Determining and verifying product provenance remains a critical challenge in global supply chains, particularly as geopolitical conflicts and shifting borders create new incentives for misrepresentation of commodities, such as hiding the origin of illegally harvested timber or stolen agricultural products. Stable Isotope Ratio Analysis (SIRA), combined with Gaussian process regression-based isoscapes, has emerged as a powerful tool for geographic origin verification. While these models are now actively deployed in operational settings supporting regulators, certification bodies, and companies, they remain constrained by data scarcity and suboptimal dataset selection. In this work, we introduce a novel deployed data valuation framework designed to enhance the selection and utilization of training data for machine learning models applied in SIRA. By quantifying the marginal utility of individual samples using Shapley values, our method guides strategic, cost-effective, and robust sampling campaigns within active monitoring programs. By prioritizing high-informative samples, our approach improves model robustness and predictive accuracy across diverse datasets and geographies. Our framework has been implemented and validated in a live provenance verification system currently used by enforcement agencies, demonstrating tangible, real-world impact. Through extensive experiments and deployment in a live provenance verification system, we show that this system significantly enhances provenance verification, mitigates fraudulent trade practices, and strengthens regulatory enforcement of global supply chains.

Dataset distillation (DD) has witnessed significant progress in creating small datasets that encapsulate rich information from large original ones. Particularly, methods based on generative priors show promising performance while maintaining computational efficiency and cross-architecture generalization. However, the generation process lacks explicit controllability for each sample. Previous distillation methods primarily match the real distribution from the perspective of the entire dataset, whereas overlooking concept completeness at the instance level. The missing or incorrectly represented object details cannot be efficiently compensated due to the constrained sample amount typical in DD settings. To this end, we propose incorporating the concept understanding of large language models (LLMs) to perform Concept-Informed Diffusion (Concord) for dataset distillation. Specifically, distinguishable and fine-grained concepts are retrieved based on category labels to inform the denoising process and refine essential object details. These concepts can be applied to any diffusion-based DD framework to enhance both the controllability and interpretability of the distilled image generation, without relying on pre-trained classifiers. We demonstrate the efficacy of Concord by achieving state-of-the-art performance on ImageNet-1K and subsets. Code is released at Concord.

The use of Artificial Intelligence (AI) and Machine Learning (ML) has been the center of the most outstanding advancements in the last years. The ability to analyze considerable streams of data in real time makes these technologies the most promising tool in many domains, including cybersecurity. As an outstanding example, ML can be used for identifying malware because of its ability to detect patterns otherwise difficult to see for humans and hardcoded rules. However, the use of AI and ML in security-relevant domains raised rightful concerns about their trustworthiness and robustness, especially when facing adaptive attackers. Additionally, privacy threats are now emerging as a crucial aspect and need proper testing and possibly mitigation to prevent data stealing and leakage of sensitive information. AISec provides a venue for presenting and discussing new developments in the intersection of security and privacy with AI and ML.

As a defense strategy against adversarial attacks, adversarial detection aims to identify and filter out adversarial data from the data flow based on discrepancies in distribution and noise patterns between natural and adversarial data. Although previous detection methods achieve high performance in detecting gradient-based adversarial attacks, new attacks based on generative models with imbalanced and anisotropic noise patterns evade detection. Even worse, the significant inference time overhead and limited performance against unseen attacks make existing techniques impractical for real-world use. In this paper, we explore the proximity relationship among adversarial noise distributions and demonstrate the existence of an open covering for these distributions. By training on the open covering of adversarial noise distributions, a detector with strong generalization performance against various types of unseen attacks can be developed. Based on this insight, we heuristically propose Perturbation Forgery, which includes noise distribution perturbation, sparse mask generation, and pseudo-adversarial data production, to train an adversarial detector capable of detecting any unseen gradient-based, generative-based, and physical adversarial attacks. Comprehensive experiments conducted on multiple general and facial datasets, with a wide spectrum of attacks, validate the strong generalization of our method.1

Feiyang Kang, Newsha Ardalani, Michael Kuchnik, Youssef Emad, Mostafa Elhoushi, Shubhabrata Sengupta, Shang-Wen Li, Ramya Raghavendra, Ruoxi Jia, Carole-Jean Wu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns.Existing data extraction methods, particularly heuristic-based divergence attacks, often exhibit limited success and offer limited insight into the fundamental drivers of memorization leakage.This paper introduces Confusion-Inducing Attacks (CIA), a principled framework for extracting memorized data by systematically maximizing model uncertainty.We empirically demonstrate that the emission of memorized text during divergence is preceded by a sustained spike in token-level prediction entropy.CIA leverages this insight by optimizing input snippets to deliberately induce this consecutive highentropy state.For aligned LLMs, we further propose mismatched Supervised Fine-tuning (SFT) to simultaneously weaken their alignment and induce targeted confusion, thereby increasing susceptibility to our attacks.Experiments on various unaligned and aligned LLMs demonstrate that our proposed attacks outperform existing baselines in extracting verbatim and near-verbatim training data without requiring prior knowledge of the training data.Our findings highlight persistent memorization risks across various LLMs and offer a more systematic method for assessing these vulnerabilities.

In recent years, text-to-image (T2I) diffusion models have gained significant attention for their ability to generate high quality images reflecting text prompts. However, their growing popularity has also led to the emergence of backdoor threats, posing substantial risks. Currently, effective defense strategies against such threats are lacking due to the diversity of backdoor targets in T2I synthesis. In this paper, we propose NaviT2I, an efficient input-level backdoor defense framework against diverse T2I backdoors. Our approach is based on the new observation that trigger tokens tend to induce significant neuron activation variation in the early stage of the diffusion generation process, a phenomenon we term Early-step Activation Variation. Leveraging this insight, NaviT2I navigates T2I models to prevent malicious inputs by analyzing Neuron activation variations caused by input tokens. Extensive experiments show that NaviT2I significantly outperforms the baselines in both effectiveness and efficiency across diverse datasets, various T2I backdoors, and different model architectures including UNet and DiT. Furthermore, we show that our method remains effective under potential adaptive attacks.

Foundation models (FMs) provide societal benefits but also amplify risks. Governments, companies, and researchers have proposed regulatory frameworks, acceptable use policies, and safety benchmarks in response. However, existing public benchmarks often define safety categories based on previous literature, intuitions, or common sense, leading to disjointed sets of categories for risks specified in recent regulations and policies, which makes it challenging to evaluate and compare FMs across these benchmarks. To bridge this gap, we introduce AIR-BENCH 2024, the first AI safety benchmark aligned with emerging government regulations and company policies, following the regulation-based safety categories grounded in the AI Risks taxonomy, AIR 2024. AIR 2024 decomposes 8 government regulations and 16 company policies into a four-tiered safety taxonomy with 314 granular risk categories in the lowest tier. AIR-BENCH 2024 contains 5,694 diverse prompts spanning these categories, with manual curation and human auditing to ensure quality. We evaluate leading language models on AIR-BENCH 2024 uncovering insights into their alignment with specified safety concerns. By bridging the gap between public benchmarks and practical AI risks, AIR-BENCH 2024 provides a foundation for assessing model safety across jurisdictions, fostering the development of safer and more responsible AI systems.

Anti-backdoor learning, aiming to train clean models directly from poisoned datasets, serves as an important defense method for backdoor attack. However, existing methods usually fail to recover backdoored samples to their original, correct labels and suffer from poor generalization to large pre-trained models due to its non end-to end training, making them unsuitable for protecting the increasingly prevalent large pre-trained models. To bridge the gap, we first revisit the anti-backdoor learning problem from a causal perspective. Our theoretical causal analysis reveals that incorporating \emph{\textbf{both}} images and the associated attack indicators preserves the model's integrity. Building on the theoretical analysis, we introduce an end-to-end method, Mind Control through Causal Inference (MCCI), to train clean models directly from poisoned datasets. This approach leverages both the image and the attack indicator to train the model. Based on this training paradigm, the model’s perception of whether an input is clean or backdoored can be controlled. Typically, by introducing fake non-attack indicators, the model perceives all inputs as clean and makes correct predictions, even for poisoned samples. Extensive experiments demonstrate that our method achieves state-of-the-art performance, efficiently recovering the original correct predictions for poisoned samples and enhancing accuracy on clean samples.

Large language models (LLMs) have demonstrated significant capabilities in natural language processing and reasoning, yet their effectiveness in autonomous planning has been under debate. While existing studies have utilized LLMs with external feedback mechanisms or in controlled environments for planning, these approaches often involve substantial computational and development resources due to the requirement for careful design and iterative backprompting. Moreover, even the most advanced LLMs like GPT-4 struggle to match human performance on standard planning benchmarks, such as the Blocksworld, without additional support. This paper investigates whether LLMs can independently generate long-horizon plans that rival human baselines. Our novel enhancements to Algorithm-of-Thoughts (AoT), which we dub AoT+, help achieve state-of-the-art results in planning benchmarks out-competing prior methods and human baselines all autonomously.

Data Shapley offers a principled framework for attributing the contribution of data within machine learning contexts. However, the traditional notion of Data Shapley requires re-training models on various data subsets, which becomes computationally infeasible for large-scale models. Additionally, this retraining-based definition cannot evaluate the contribution of data for a specific model training run, which may often be of interest in practice. This paper introduces a novel concept, In-Run Data Shapley, which eliminates the need for model retraining and is specifically designed for assessing data contribution for a particular model of interest. In-Run Data Shapley calculates the Shapley value for each gradient update iteration and accumulates these values throughout the training process. We present several techniques that allow the efficient scaling of In-Run Data Shapley to the size of foundation models. In its most optimized implementation, our method adds negligible runtime overhead compared to standard model training. This dramatic efficiency improvement makes it possible to perform data attribution for the foundation model pretraining stage. We present several case studies that offer fresh insights into pretraining data's contribution and discuss their implications for copyright in generative AI and pretraining data curation.

Traditional data influence estimation methods, like influence function, assume that learning algorithms are permutation-invariant with respect to training data. However, modern training paradigms—especially for foundation models using stochastic algorithms and non-convergent, multi-stage curricula—are sensitive to data ordering, thus violating this assumption. This mismatch renders influence functions inadequate for answering some critical questions in current machine learning: How can we differentiate the influence of the same data contributing at different stages of training? More generally, how can we capture the dependence of data influence on the optimization trajectory during training? To address this gap, we formalize the concept of \emph{trajectory-specific leave-one-out (LOO) influence}, which quantifies the impact of removing a data point from a specific iteration during training, accounting for the exact sequence of data encountered and the model's optimization trajectory. However, exactly evaluating the trajectory-specific LOO presents a significant computational challenge. To address this, we propose \emph{data value embedding}, a novel technique enabling efficient approximation of trajectory-specific LOO. Specifically, we compute a training data embedding that encapsulates the cumulative interactions between data and the evolving model parameters. The LOO can then be efficiently approximated through a simple dot-product between the data value embedding and the gradient of the given test data. As data value embedding captures training data ordering, it offers valuable insights into model training dynamics. In particular, we uncover distinct phases of data influence, revealing that data points in the early and late stages of training exert a greater impact on the final model. These insights translate into actionable strategies for managing the computational overhead of data selection by strategically timing the selection process, potentially opening new avenues in data curation research.

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with **SORRY-Bench**, our proposed benchmark. **First**, existing methods often use coarse-grained taxonomies of unsafe topics, and are over-representing some fine-grained topics. For example, among the ten existing datasets that we evaluated, tests for refusals of self-harm instructions are over 3x less represented than tests for fraudulent activities. SORRY-Bench improves on this by using a fine-grained taxonomy of 44 potentially unsafe topics, and 440 class-balanced unsafe instructions, compiled through human-in-the-loop methods. **Second**, evaluations often overlook the linguistic formatting of prompts, like different languages, dialects, and more --- which are only implicitly considered in many evaluations. We supplement SORRY-bench with 20 diverse linguistic augmentations to systematically examine these effects. **Third**, existing evaluations rely on large LLMs (e.g., GPT-4) for evaluation, which can be computationally expensive. We investigate design choices for creating a fast, accurate automated safety evaluator. By collecting 7K+ human annotations and conducting a meta-evaluation of diverse LLM-as-a-judge designs, we show that fine-tuned 7B LLMs can achieve accuracy comparable to GPT-4 scale LLMs, with lower computational cost. Putting these together, we evaluate over 50 proprietary and open-weight LLMs on SORRY-Bench, analyzing their distinctive safety refusal behaviors. We hope our effort provides a building block for systematic evaluations of LLMs' safety refusal capabilities, in a balanced, granular, and efficient manner. Benchmark demo, data, code, and models are available through [https://sorry-bench.github.io](https://sorry-bench.github.io).

Safety alignment is crucial for Large Language Models (LLMs) to resist malicious instructions but often results in over-refusals, where benign prompts are unnecessarily rejected, impairing user experience and model utility. To this end, we introduce ACTOR (Activation-Based Training for Over-Refusal Reduction), a robust and compute- and-data efficient training framework that mini- mizes over-refusals by utilizing internal activation patterns from diverse queries. ACTOR precisely identifies and adjusts the activation components that trigger refusals, providing stronger control over the refusal mechanism. By fine-tuning only a single model layer, ACTOR effectively reduces over-refusals across multiple benchmarks while maintaining the model’s ability to handle harmful queries and preserving overall utility.

Large language models (LLMs) are making inroads into classical AI problems such as automated planning, yet key shortcomings continue to hamper their integration. Chain-of-Thought (CoT) struggles in complex multi-step reasoning, and Tree-of-Thoughts requires multiple queries that increase computational overhead. Recently, Algorithm-of-Thoughts (AoT) have shown promise using in-context examples, at the cost of significantly longer solutions compared to CoT. Aimed at bridging the solution length gap between CoT and AoT, this paper introduces AoT-O3, which combines supervised finetuning on AoT-style plans with a reinforcement learning (RL) framework designed to reduce solution length. The RL component uses a reward model that favors concise, valid solutions while maintaining planning accuracy. Empirical evaluations indicate that AoT-O3 shortens solution length by up to 80\% compared to baseline AoT while maintaining or surpassing prior performance. These findings suggest a promising pathway for more efficient, scalable LLM-based planning.

We argue that the machine learning value chain is structurally unsustainable due to an economic data processing inequality: each state in the data cycle from inputs to model weights to synthetic outputs refines technical signal but strips economic equity from data generators. We show, by analyzing seventy-three public data deals, that the majority of value accrues to aggregators, with documented creator royalties rounding to zero and widespread opacity of deal terms. This is not just an economic welfare concern: as data and its derivatives become economic assets, the feedback loop that sustains current learning algorithms is at risk. We identify three structural faults - missing provenance, asymmetric bargaining power, and non-dynamic pricing - as the operational machinery of this inequality. In our analysis, we trace these problems along the machine learning value chain and propose an Equitable Data-Value Exchange (EDVEX) Framework to enable a minimal market that benefits all participants. Finally, we outline research directions where our community can make concrete contributions to data deals and contextualize our position with related and orthogonal viewpoints.

Machine unlearning has emerged as a prevalent technical solution for selectively removing unwanted knowledge absorbed during pre-training, without requiring full retraining. While recent unlearning techniques can effectively remove undesirable content without severely compromising performance on standard benchmarks, we find that they may inadvertently create ``knowledge holes''---unintended losses of benign knowledge that standard benchmarks fail to capture. To probe where unlearned models reveal knowledge holes, we propose a test case generation framework that explores both immediate neighbors of unlearned content and broader areas of potential failures. Our evaluation demonstrates significant hidden costs of unlearning: up to 98.7\% of the test cases yield irrelevant or nonsensical responses from unlearned models, despite being answerable by the pretrained model. These findings necessitate rethinking the conventional approach to evaluating knowledge preservation in unlearning, moving beyond standard, static benchmarks.

The advancement of smart grids presents both vast opportunities and heightened cybersecurity risks. Data-driven defense mechanisms, though designed as a shield against these threats, can fall prey to poisoning attacks. We delve into regression settings, underscoring the imperative to fortify defenses against a spectrum of poison ratios, notably those above 0.5—an issue scarcely addressed in prior studies. Recognizing the susceptibilities of smart grids and their manipulable sensors, we exploit the very intent of poisoning attacks, compromising model accuracy, as our defense mechanism. Our proposed two-level optimization framework discerns between poisoned and authentic data based on model residuals, outperforming or matching existing methods in 72% to 77% of precision and 75% to 80% of recalls across various poisoning attacks, poison ratios, and datasets. Once the authentic data are identified, the trained model is adaptable for a variety of applications. Comprehensive evaluations on different smart grid datasets, pitted against myriad poisoning schemes, validate our methodology’s edge over existing methods. We also shed light on the implications of model misspecification originating from temporal auto-correlation, a common feature in IoT and smart grid data.

Most traditional AI safety research views models as machines and centers on algorithmfocused attacks developed by security experts.As large language models (LLMs) become increasingly common and competent, non-expert users can also impose risks during daily interactions.Observing this, we shift the perspective, by treating LLMs as human-like communicators to examine the interplay between everyday language interaction and AI safety.Specifically, we study how to persuade LLMs to jailbreak them.First, we propose a persuasion taxonomy derived from decades of social science research.Then, we apply the taxonomy to automatically generate persuasive adversarial prompts (PAP) to jailbreak LLMs.Results show that persuasion significantly increases the jailbreak risk across all risk categories: PAP consistently achieves an attack success rate of over 92% on Llama-2-7b-Chat, GPT-3.5, and GPT-4 in 10 trials, surpassing recent algorithm-focused attacks.On the defense side, we explore various mechanisms against PAP, find a significant gap in existing defenses, and advocate for more fundamental solutions for AI safety 1 .

Bilgehan Sel, Priya Shanmugasundaram, Mohammad Kachuee, Kun Zhou, Ruoxi Jia, Ming Jin. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on predictions made by these models is crucial for improving their trustworthiness. Current influence estimation techniques involve computing gradients for every training point or repeated training on different subsets. These approaches face obvious computational challenges when scaled up to large datasets and models. In this paper, we introduce and explore the Mirrored Influence Hypothesis, highlighting a reciprocal nature of influence between training and test data. Specifically, it sug-gests that evaluating the influence of training data on test predictions can be reformulated as an equivalent, yet inverse problem: assessing how the predictions for training samples would be altered if the model were trained on specific test samples. Through both empirical and theoretical validations, we demonstrate the wide applicability of our hypothesis. Inspired by this, we introduce a new method for estimating the influence of training data, which requires calculating gradients for specific test samples, paired with a forward pass for each training point. This approach can capitalize on the common asymmetry in scenarios where the number of test samples under concurrent examination is much smaller than the scale of the training dataset, thus gaining a significant improvement in efficiency compared to existing approaches. We demonstrate the applicability of our method across a range of scenarios, including data attribution in diffusion models, data leakage detection, analy-sis of memorization, mislabeled data detection, and tracing behavior in language models.

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions.The high dimensionality of potential triggers in the token space and the diverse range of malicious behaviors make this a critical challenge.We present BEEAR, a mitigation approach leveraging the insight that backdoor triggers induce relatively uniform drifts in the model's embedding space.Our bilevel optimization method identifies universal embedding perturbations that elicit unwanted behaviors and adjusts the model parameters to reinforce safe behaviors against these perturbations.Experiments show BEEAR reduces the success rate of RLHF time backdoor attacks from >95% to <1% and from 47% to 0% for instruction-tuning time backdoors targeting malicious code generation, without compromising model utility.Requiring only defender-defined safe and unwanted behaviors, BEEAR represents a step towards practical defenses against safety backdoors in LLMs, providing a foundation for further advancements in AI safety and security.* W. Sun and Y. Zeng contributed equally.Corresponding Y.

Text summarization, a key natural language generation (NLG) task, is vital in various domains.However, the high cost of inaccurate summaries in risk-critical applications, particularly those involving human-in-the-loop decision-making, raises concerns about the reliability of uncertainty estimation on text summarization (UE-TS) evaluation methods.This concern stems from the dependency of uncertainty model metrics on diverse and potentially conflicting NLG metrics.To address this issue, we introduce a comprehensive UE-TS benchmark incorporating 31 NLG metrics across four dimensions.The benchmark evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets, with humanannotation analysis incorporated where applicable.We also assess the performance of 14 common uncertainty estimation methods within this benchmark.Our findings emphasize the importance of considering multiple uncorrelated NLG metrics and diverse uncertainty estimation methods to ensure reliable and efficient evaluation of UE-TS techniques.Our code and data are available here.

This work focuses on leveraging and selecting from vast, unlabeled, open data to *pre-fine-tune* a pre-trained language model. The goal is to minimize the need for costly domain-specific data for subsequent fine-tuning while achieving desired performance levels. While many data selection algorithms have been designed for small-scale applications, rendering them unsuitable for our context, some emerging methods do cater to language data scales. However, they often prioritize data that aligns with the target distribution. While this strategy may be effective when training a model from scratch, it can yield limited results when the model has already been pre-trained on a different distribution. Differing from prior work, our key idea is to select data that nudges the pre-training distribution closer to the target distribution. We show the optimality of this approach for fine-tuning tasks under certain conditions. We demonstrate the efficacy of our methodology across a diverse array of tasks (NLU, NLG, zero-shot) with models up to 2.7B, showing that it consistently surpasses other selection methods. Moreover, our proposed method is significantly faster than existing techniques, scaling to millions of samples within a single GPU hour. Our code is open-sourced. While fine-tuning offers significant potential for enhancing performance across diverse tasks, its associated costs often limit its widespread adoption; with this work, we hope to lay the groundwork for cost-effective fine-tuning, making its benefits more accessible.

Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open-source release of Llama models and OpenAI's APIs for fine-tuning GPT-3.5 Turbo on customized datasets accelerate this trend. But, what are the safety costs associated with such customized fine-tuning? While existing safety alignment techniques restrict harmful behaviors of LLMs at inference time, they do not cover safety risks when fine-tuning privileges are extended to end-users. Our red teaming studies find that the safety alignment of LLMs can be compromised by fine-tuning with only a few adversarially designed training examples. For instance, we jailbreak GPT-3.5 Turbo's safety guardrails by fine-tuning it on only 10 such examples at a cost of less than $0.20 via OpenAI's APIs, making the model responsive to nearly any harmful instructions. Disconcertingly, our research also reveals that, even without malicious intent, simply fine-tuning with benign and commonly used datasets can also inadvertently degrade the safety alignment of LLMs, though to a lesser extent. These findings suggest that fine-tuning aligned LLMs introduces new safety risks that current safety infrastructures fall short of addressing --- even if a model's initial safety alignment is impeccable, how can it be maintained after customized fine-tuning? We outline and critically analyze potential mitigations and advocate for further research efforts toward reinforcing safety protocols for the customized fine-tuning of aligned LLMs. (This paper contains red-teaming data and model-generated content that can be offensive in nature.)

Independent evaluation and red teaming are critical for identifying the risks posed by generative AI systems. However, the terms of service and enforcement strategies used by prominent AI companies to deter model misuse have disincentives on good faith safety evaluations. This causes some researchers to fear that conducting such research or releasing their findings will result in account suspensions or legal reprisal. Although some companies offer researcher access programs, they are an inadequate substitute for independent research access, as they have limited community representation, receive inadequate funding, and lack independence from corporate incentives. We propose that major generative AI developers commit to providing a legal and technical safe harbor, protecting public interest safety research and removing the threat of account suspensions or legal reprisal. These proposals emerged from our collective experience conducting safety, privacy, and trustworthiness research on generative AI systems, where norms and incentives could be better aligned with public interests, without exacerbating model misuse. We believe these commitments are a necessary step towards more inclusive and unimpeded community efforts to tackle the risks of generative AI.

Current literature, aiming to surpass the "Chain-of-Thought" approach, often resorts to external modi operandi involving halting, modifying, and then resuming the generation process to boost Large Language Models’ (LLMs) reasoning capacities. Due to their myopic perspective, they escalate the number of query requests, leading to increased costs, memory, and computational overheads. Addressing this, we propose the Algorithm of Thoughts—a novel strategy that propels LLMs through algorithmic reasoning pathways. By employing algorithmic examples fully in-context, this overarching view of the whole process exploits the innate recurrence dynamics of LLMs, expanding their idea exploration with merely one or a few queries. Our technique outperforms earlier single-query methods and even more recent multi-query strategies that employ an extensive tree search algorithms while using significantly fewer tokens. Intriguingly, our results suggest that instructing an LLM using an algorithm can lead to performance surpassing that of the algorithm itself, hinting at LLM’s inherent ability to weave its intuition into optimized searches. We probe into the underpinnings of our method’s efficacy and its nuances in application. The code and related content can be found in: https://algorithm-of-thoughts.github.io

Data Shapley provides a principled approach to data valuation and plays a crucial role in data-centric machine learning (ML) research. Data selection is considered a standard application of Data Shapley. However, its data selection performance has shown to be inconsistent across settings in the literature. This study aims to deepen our understanding of this phenomenon. We introduce a hypothesis testing framework and show that Data Shapley’s performance can be no better than random selection without specific constraints on utility functions. We identify a class of utility functions, monotonically transformed modular functions, within which Data Shapley optimally selects data. Based on this insight, we propose a heuristic for predicting Data Shapley’s effectiveness in data selection tasks. Our experiments corroborate these findings, adding new insights into when Data Shapley may or may not succeed.

Recent advancements in Large Language Models (LLMs) have showcased remarkable capabilities across various tasks in different domains. However, the emergence of biases and the potential for generating harmful content in LLMs, particularly under malicious inputs, pose significant challenges. Current mitigation strategies, while effective, are not resilient under adversarial attacks. This paper introduces Resilient Guardrails for Large Language Models (RigorLLM), a novel framework designed to efficiently and effectively moderate harmful and unsafe inputs and outputs for LLMs. By employing a multi-faceted approach that includes energy-based training data augmentation through Langevin dynamics, optimizing a safe suffix for inputs via minimax optimization, and integrating a fusion-based model combining robust KNN with LLMs based on our data augmentation, RigorLLM offers a robust solution to harmful content moderation. Our experimental evaluations demonstrate that RigorLLM not only outperforms existing baselines like OpenAI API and Perspective API in detecting harmful content but also exhibits unparalleled resilience to jailbreaking attacks. The innovative use of constrained optimization and a fusion-based guardrail approach represents a significant step forward in developing more secure and reliable LLMs, setting a new standard for content moderation frameworks in the face of evolving digital threats.

To address issues of group-level fairness in machine learning, it is natural to adjust model parameters based on specific fairness objectives over a sensitive-attributed validation set. Such an adjustment procedure can be cast within a meta-learning framework. However, naive integration of fairness goals via meta-learning can cause hypergradient conflicts for subgroups, resulting in unstable convergence and compromising model performance and fairness. To navigate this issue, we frame the resolution of hypergradient conflicts as a multi-player cooperative bargaining game. We introduce a two-stage meta-learning framework in which the first stage involves the use of a Nash Bargaining Solution (NBS) to resolve hypergradient conflicts and steer the model toward the Pareto front, and the second stage optimizes with respect to specific fairness goals. Our method is supported by theoretical results, notably a proof of the NBS for gradient aggregation free from linear independence assumptions, a proof of Pareto improvement, and a proof of monotonic improvement in validation loss. We also show empirical effects across various fairness objectives in six key fairness datasets and two image classification tasks.

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns. Driven by these concerns, machine unlearning has become crucial to effectively purge undesirable knowledge from models. While existing literature has studied various unlearning techniques, these often suffer from either poor unlearning quality or degradation in text-image alignment after unlearning, due to the competitive nature of these objectives. To address these challenges, we propose a framework that seeks an optimal model update at each unlearning iteration, ensuring monotonic improvement on both objectives. We further derive the characterization of such an update. In addition, we design procedures to strategically diversify the unlearning and remaining datasets to boost performance improvement. Our evaluation demonstrates that our method effectively removes target classes from recent diffusion-based generative models and concepts from stable diffusion models while maintaining close alignment with the models' original trained states, thus outperforming state-of-the-art baselines.

Online batch selection methods offer an adaptive alternative to static training data selection by dynamically selecting data batches during training. However, existing methods either rely on impractical reference models or simple heuristics that may not capture true data informativeness. To address these limitations, we propose \emph{GREedy Approximation Taylor Selection} (GREATS), a principled and efficient online batch selection method that applies greedy algorithm to optimize the data batch quality approximated by Taylor expansion. We develop a series of techniques to scale GREATS to large-scale model training. Extensive experiments with large language models (LLMs) demonstrate that GREATS significantly improves training convergence speed and generalization performance.

Active learning is a promising paradigm for reducing labeling costs by strategically requesting labels to improve model performance. However, existing active learning methods often rely on expensive acquisition functions, extensive model retraining, and multiple rounds of interaction with annotators. To address these limitations, we propose a novel approach for active learning, which aims to select batches of unlabeled instances through a learned surrogate model for data acquisition. A key challenge in this approach is to develop an acquisition function that generalizes well, as the history of data, which forms part of the utility function’s input, grows over time. Our novel algorithmic contribution is a multi-task bilevel optimization framework that predicts the relative utility—measured by the validation accuracy—of different training sets, and ensures the learned acquisition function generalizes effectively. For cases where validation accuracy is expensive to evaluate, we introduce efficient interpolation-based surrogate models to estimate the utility function, reducing the evaluation cost. We demonstrate the performance of our approach through extensive experiments on standard active classification benchmarks.

We study the expressibility and learnability of solution functions of convex optimization and their multi-layer architectural extension. The main results are: (1) the class of solution functions of linear programming (LP) and quadratic programming (QP) is a universal approximant for the smooth model class or some restricted Sobolev space, and we characterize the rate-distortion, (2) the approximation power is investigated through a viewpoint of regression error, where information about the target function is provided in terms of data observations, (3) compositionality in the form of deep architecture with optimization as a layer is shown to reconstruct some basic functions used in numerical analysis without error, which implies that (4) a substantial reduction in rate-distortion can be achieved with a universal network architecture, and (5) we discuss the statistical bounds of empirical covering numbers for LP/QP, as well as a generic optimization problem (possibly nonconvex) by exploiting tame geometry. Our results provide the **first rigorous analysis of the approximation and learning-theoretic properties of solution functions** with implications for algorithmic design and performance guarantees.

Data valuation has wide use cases in machine learning, including improving data quality and creating economic incentives for data sharing. This paper studies the robustness of data valuation to noisy model performance scores. Particularly, we find that the inherent randomness of the widely used stochastic gradient descent can cause existing data value notions (e.g., the Shapley value and the Leave-one-out error) to produce inconsistent data value rankings across different runs. To address this challenge, we introduce the concept of safety margin, which measures the robustness of a data value notion. We show that the Banzhaf value, a famous value notion that originated from cooperative game theory literature, achieves the largest safety margin among all semivalues (a class of value notions that satisfy crucial properties entailed by ML applications and include the famous Shapley value and Leave-one-out error). We propose an algorithm to efficiently estimate the Banzhaf value based on the Maximum Sample Reuse (MSR) principle. Our evaluation demonstrates that the Banzhaf value outperforms the existing semivalue-based data value notions on several ML tasks such as learning with weighted samples and noisy label detection. Overall, our study suggests that when the underlying ML algorithm is stochastic, the Banzhaf value is a promising alternative to the other semivalue-based data value schemes given its computational advantage and ability to robustly differentiate data quality.

Backdoor attacks introduce manipulated data into a machine learning model's training set, causing the model to misclassify inputs with a trigger during testing to achieve a desired outcome by the attacker. For backdoor attacks to bypass human inspection, it is essential that the injected data appear to be correctly labeled. The attacks with such property are often referred to as "clean-label attacks." The success of current clean-label backdoor methods largely depends on access to the complete training set. Yet, accessing the complete dataset is often challenging or unfeasible since it frequently comes from varied, independent sources, like images from distinct users. It remains a question of whether backdoor attacks still present real threats.

Membership inference attacks (MIAs) aim to infer whether a data point has been used to train a machine learning model. These attacks can be employed to identify potential privacy vulnerabilities and detect unauthorized use of personal data. While MIAs have been traditionally studied for simple classification models, recent advancements in multi-modal pre-training, such as CLIP, have demonstrated remarkable zero-shot performance across a range of computer vision tasks. However, the sheer scale of data and models presents significant computational challenges for performing the attacks.This paper takes a first step towards developing practical MIAs against large-scale multi-modal models. We introduce a simple baseline strategy by thresholding the cosine similarity between text and image features of a target point and propose further enhancing the baseline by aggregating cosine similarity across transformations of the target. We also present a new weakly supervised attack method that leverages ground-truth non-members (e.g., obtained by using the publication date of a target model and the timestamps of the open data) to further enhance the attack. Our evaluation shows that CLIP models are susceptible to our attack strategies, with our simple baseline achieving over 75% membership identification accuracy. Furthermore, our enhanced attacks outperform the baseline across multiple models and datasets, with the weakly supervised attack demonstrating an average-case performance improvement of 17% and being at least 7X more effective at low false-positive rates. These findings highlight the importance of protecting the privacy of multi-modal foundational models, which were previously assumed to be less susceptible to MIAs due to less overfitting. Our code is available at https://github.com/ruoxi-jia-group/CLIP-MIA.

Data-free knowledge distillation (KD) helps transfer knowledge from a pre-trained model (known as the teacher model) to a smaller model (known as the student model) without access to the original training data used for training the teacher model. However, the security of the synthetic or out-of-distribution (OOD) data required in data-free KD is largely unknown and under-explored. In this work, we make the first effort to uncover the security risk of data-free KD w.r.t. untrusted pre-trained models. We then propose Anti-Backdoor Data-Free KD (ABD), the first plug-in defensive method for data-free KD methods to mitigate the chance of potential backdoors being transferred. We empirically evaluate the effectiveness of our proposed ABD in diminishing transferred backdoor knowledge while maintaining compatible downstream performances as the vanilla KD. We envision this work as a milestone for alarming and mitigating the potential backdoors in data-free KD. Codes are released at https://github.com/illidanlab/ABD .

Data valuation—quantifying the contribution of individual data sources to certain predictive behaviors of a model—is of great importance to enhancing the transparency of machine learning and designing incentive systems for data sharing. Existing work has focused on evaluating data sources with the shared feature or sample space. How to valuate fragmented data sources of which each only contains partial features and samples remains an open question. We start by presenting a method to calculate the counterfactual of removing a fragment from the aggregated data matrix. Based on the counterfactual calculation, we further propose 2D-Shapley, a theoretical framework for fragmented data valuation that uniquely satisfies some appealing axioms in the fragmented data context. 2D-Shapley empowers a range of new use cases, such as selecting useful data fragments, providing interpretation for sample-wise data values, and fine-grained data issue diagnosis.

Traditionally, data selection has been studied in settings where all samples from prospective sources are fully revealed to a machine learning developer. However, in practical data exchange scenarios, data providers often reveal only a limited subset of samples before an acquisition decision is made. Recently, there have been efforts to fit scaling functions that predict model performance at any *size and data source composition* using the limited available samples. However, these scaling functions are usually black-box, computationally expensive to fit, highly susceptible to overfitting, or/and difficult to optimize for data selection. This paper proposes a framework called *<projektor>*, which predicts model performance and supports data selection decisions based on partial samples of prospective data sources. Our approach distinguishes itself from existing work by introducing a novel *two-stage* performance inference process. In the first stage, we leverage the Optimal Transport distance to predict the model's performance for any data mixture ratio within the range of disclosed data sizes. In the second stage, we extrapolate the performance to larger undisclosed data sizes based on a novel parameter-free mapping technique inspired by neural scaling laws. We further derive an efficient gradient-based method to select data sources based on the projected model performance. Evaluation over a diverse range of applications (e.g., vision, text, fine-tuning, noisy data sources, etc.) demonstrates that *<projektor>* significantly improves existing performance scaling approaches in terms of both the accuracy of performance inference and the computation costs associated with constructing the performance predictor. Also, *<projektor>* outperforms by a wide margin in data selection effectiveness compared to a range of other off-the-shelf solutions. We provide *<projektor>* an open-source toolkit.

Data valuation, a growing field that aims at quantifying the usefulness of individual data sources for training machine learning (ML) models, faces notable yet often overlooked privacy challenges. This paper studies these challenges with a focus on KNN-Shapley, one of the most practical data valuation methods nowadays. We first emphasize the inherent privacy risks of KNN-Shapley, and demonstrate the significant technical challenges in adapting KNN-Shapley to accommodate differential privacy (DP). To overcome these challenges, we introduce TKNN-Shapley, a refined variant of KNN-Shapley that is privacy-friendly, allowing for straightforward modifications to incorporate DP guarantee (DP-TKNN-Shapley). We show that DP-TKNN-Shapley has several advantages and offers a superior privacy-utility tradeoff compared to naively privatized KNN-Shapley. Moreover, even non-private TKNN-Shapley matches KNN-Shapley's performance in discerning data quality. Overall, our findings suggest that TKNN-Shapley is a promising alternative to KNN-Shapley, particularly for real-world applications involving sensitive data.

Bounding privacy leakage over compositions, i.e., privacy accounting, is a key challenge in differential privacy (DP). However, the privacy parameter ($\varepsilon$ or $\delta$) is often easy to estimate but hard to bound. In this paper, we propose a new differential privacy paradigm called estimate-verify-release (EVR), which tackles the challenges of providing a strict upper bound for the privacy parameter in DP compositions by converting an *estimate* of privacy parameter into a formal guarantee. The EVR paradigm first verifies whether the mechanism meets the *estimated* privacy guarantee, and then releases the query output based on the verification result. The core component of the EVR is privacy verification. We develop a randomized privacy verifier using Monte Carlo (MC) technique. Furthermore, we propose an MC-based DP accountant that outperforms existing DP accounting techniques in terms of accuracy and efficiency. MC-based DP verifier and accountant is applicable to an important and commonly used class of DP algorithms, including the famous DP-SGD. An empirical evaluation shows the proposed EVR paradigm improves the utility-privacy tradeoff for privacy-preserving machine learning.

Machine learning (ML) models can expose the private information of training data when confronted with privacy attacks. Specifically, a malicious user with black-box access to a ML-as-a-service platform can reconstruct the training data (i.e., model inversion attacks) or infer the membership information (i.e., membership inference attacks) simply by querying the ML model. Despite the pressing need for effective defenses against privacy attacks with black-box access, existing approaches have mostly focused on enhancing the robustness of the ML model via modifying the model training process or the model prediction process. These defenses can compromise model utility and require the cooperation of the underlying AI platform (i.e., platform-dependent). These constraints largely limit the real-world applicability of existing defenses.

Recent studies show that the state-of-the-art deep neural networks are vulnerable to model inversion attacks, in which access to a model is abused to reconstruct private training data of any given target class. Existing attacks rely on having access to either the complete target model (whitebox) or the model's soft-labels (blackbox). However, no prior work has been done in the harder but more practical scenario, in which the attacker only has access to the model's predicted label, without a confidence measure. In this paper, we introduce an algorithm, Boundary-Repelling Model Inversion (BREP-MI), to invert private training data using only the target model's predicted labels. The key idea of our algorithm is to evaluate the model's predicted labels over a sphere and then estimate the direction to reach the target class's centroid. Using the example of face recognition, we show that the images reconstructed by BREP-MI successfully reproduce the semantics of the private training data for various datasets and target model architectures. We compare BREP-MI with the state-of-the-art white-box and blackbox model inversion attacks, and the results show that despite assuming less knowledge about the target model, BREP-MI outperforms the blackbox attack and achieves comparable results to the whitebox attack. Our code is available online.11https://github.com/m-kahla/Label-Only-Model-Inversion-Attacks-via-Boundary-Repulsion

Protecting large language models from privacy leakage is becoming increasingly crucial with their wide adoption in real-world products.Yet applying differential privacy (DP), a canonical notion with provable privacy guarantees for machine learning models, to those models remains challenging due to the trade-off between model utility and privacy loss.Utilizing the fact that sensitive information in language data tends to be sparse, Shi et al. (2021) formalized a DP notion extension called Selective Differential Privacy (SDP) to protect only the sensitive tokens defined by a policy function.However, their algorithm only works for RNN-based models.In this paper, we develop a novel framework, Just Fine-tune Twice (JFT), that achieves SDP for state-of-the-art large transformer-based models.Our method is easy to implement: it first finetunes the model with redacted in-domain data, and then fine-tunes it again with the original in-domain data using a private training mechanism.Furthermore, we study the scenario of imperfect implementation of policy functions that misses sensitive tokens and develop systematic methods to handle it.Experiments show that our method achieves strong utility compared to previous baselines.We also analyze the SDP privacy guarantee empirically with the canary insertion attack 1 .

With the increasing applications of language models, it has become crucial to protect these models from leaking private information.Previous work has attempted to tackle this challenge by training RNN-based language models with differential privacy guarantees.However, applying classical differential privacy to language models leads to poor model performance as the underlying privacy notion is over-pessimistic and provides undifferentiated protection for all tokens in the data.Given that the private information in natural language is sparse (for example, the bulk of an email might not carry personally identifiable information), we propose a new privacy notion, selective differential privacy, to provide rigorous privacy guarantees on the sensitive portion of the data to improve model utility.To realize such a new notion, we develop a corresponding privacy mechanism, Selective-DPSGD, for RNN-based language models.Besides language modeling, we also apply the method to a more concrete application -dialog systems.Experiments on both language modeling and dialog system building show that the proposed privacy-preserving mechanism achieves better utilities while remaining safe under various privacy attacks compared to the baselines.The data and code are released to facilitate future research 1 .

Previous works have validated that text generation APIs can be stolen through imitation attacks, causing IP violations. In order to protect the IP of text generation APIs, recent work has introduced a watermarking algorithm and utilized the null-hypothesis test as a post-hoc ownership verification on the imitation models. However, we find that it is possible to detect those watermarks via sufficient statistics of the frequencies of candidate watermarking words. To address this drawback, in this paper, we propose a novel Conditional wATERmarking framework (CATER) for protecting the IP of text generation APIs. An optimization method is proposed to decide the watermarking rules that can minimize the distortion of overall word distributions while maximizing the change of conditional word selections. Theoretically, we prove that it is infeasible for even the savviest attacker (they know how CATER works) to reveal the used watermarks from a large pool of potential word pairs based on statistical inspection. Empirically, we observe that high-order conditions lead to an exponential growth of suspicious (unused) watermarks, making our crafted watermarks more stealthy. In addition, CATER can effectively identify IP infringement under architectural mismatch and cross-domain imitation attacks, with negligible impairments on the generation quality of victim APIs. We envision our work as a milestone for stealthily protecting the IP of text generation APIs.

Propose-Test-Release (PTR) is a differential privacy framework that works with local sensitivity of functions, instead of their global sensitivity. This framework is typically used for releasing robust statistics such as median or trimmed mean in a differentially private manner. While PTR is a common framework introduced over a decade ago, using it in applications such as robust SGD where we need many adaptive robust queries is challenging. This is mainly due to the lack of \Renyi Differential Privacy (RDP) analysis, an essential ingredient underlying the moments accountant approach for differentially private deep learning. In this work, we generalize the standard PTR and derive the first RDP bound for it. We show that our RDP bound for PTR yields tighter DP guarantees than the directly analyzed $(\varepsilon, \delta)$-DP. We also derive the algorithm-specific privacy amplification bound of PTR under subsampling. We show that our bound is much tighter than the general upper bound and close to the lower bound. Our RDP bounds enable tighter privacy loss calculation for the composition of many adaptive runs of PTR. As an application of our analysis, we show that PTR and our theoretical results can be used to design differentially private variants for byzantine robust training algorithms that use robust statistics for gradients aggregation. We conduct experiments on the settings of label, feature, and gradient corruption across different datasets and architectures. We show that PTR-based private and robust training algorithm significantly improves the utility compared with the baseline.

This paper studies defense mechanisms against model inversion (MI) attacks -- a type of privacy attacks aimed at inferring information about the training data distribution given the access to a target machine learning model. Existing defense mechanisms rely on model-specific heuristics or noise injection. While being able to mitigate attacks, existing methods significantly hinder model performance. There remains a question of how to design a defense mechanism that is applicable to a variety of models and achieves better utility-privacy tradeoff. In this paper, we propose the Mutual Information Regularization based Defense (MID) against MI attacks. The key idea is to limit the information about the model input contained in the prediction, thereby limiting the ability of an adversary to infer the private training attributes from the model prediction. Our defense principle is model-agnostic and we present tractable approximations to the regularizer for linear regression, decision trees, and neural networks, which have been successfully attacked by prior work if not attached with any defenses. We present a formal study of MI attacks by devising a rigorous game-based definition and quantifying the associated information leakage. Our theoretical analysis sheds light on the inefficacy of DP in defending against MI attacks, which has been empirically observed in several prior works. Our experiments demonstrate that MID leads to state-of-the-art performance for a variety of MI attacks, target models and datasets.

Training deep neural networks from scratch could be computationally expensive and requires a lot of training data. Recent work has explored different watermarking techniques to protect the pre-trained deep neural networks from potential copyright infringements. However, these techniques could be vulnerable to watermark removal attacks. In this work, we propose REFIT, a unified watermark removal framework based on fine-tuning, which does not rely on the knowledge of the watermarks, and is effective against a wide range of watermarking schemes. In particular, we conduct a comprehensive study of a realistic attack scenario where the adversary has limited training data, which has not been emphasized in prior work on attacks against watermarking schemes. To effectively remove the watermarks without compromising the model functionality under this weak threat model, we propose two techniques that are incorporated into our fine-tuning framework: (1) an adaption of the elastic weight consolidation (EWC) algorithm, which is originally proposed for mitigating the catastrophic forgetting phenomenon; and (2) unlabeled data augmentation (AU), where we leverage auxiliary unlabeled data from other sources. Our extensive evaluation shows the effectiveness of REFIT against diverse watermark embedding schemes. In particular, both EWC and AU significantly decrease the amount of labeled training data needed for effective watermark removal, and the unlabeled data samples used for AU do not necessarily need to be drawn from the same distribution as the benign data for model evaluation. The experimental results demonstrate that our fine-tuning based watermark removal attacks could pose real threats to the copyright of pre-trained models, and thus highlight the importance of further investigating the watermarking problem and proposing more robust watermark embedding schemes against the attacks.

Quantifying the importance of each training point to a learning task is a fundamental problem in machine learning and the estimated importance scores have been leveraged to guide a range of data workflows such as data summarization and domain adaption. One simple idea is to use the leave-one-out error of each training point to indicate its importance. Recent work has also proposed to use the Shapley value, as it defines a unique value distribution scheme that satisfies a set of appealing properties. However, calculating Shapley values is often expensive, which limits its applicability in real-world applications at scale. Multiple heuristics to improve the scalability of calculating Shapley values have been proposed recently, with the potential risk of compromising their utility in real-world applications.How well do existing data quantification methods perform on existing workflows? How do these methods compare with each other, empirically and theoretically? Must we sacrifice scalability for the utility in these workflows when using these methods? In this paper, we conduct a novel theoretical analysis comparing the utility of different importance quantification methods, and report extensive experimental studies on existing and proposed workflows such as noisy label detection, watermark removal, data summarization, data acquisition, and domain adaptation. We show that Shapley value approximation based on a KNN surrogate over pretrained feature embeddings obtains comparable utility with existing algorithms while achieving significant scalability improvement, often by orders of magnitude. Our theoretical analysis also justifies its advantage over the leave-one-out error.The code is available at https://github.com/AIsecure/Shapley-Study.

Model inversion (MI) attacks are aimed at reconstructing training data from model parameters. Such attacks have triggered increasing concerns about privacy, especially given a growing number of online model repositories. However, existing MI attacks against deep neural networks (DNNs) have large room for performance improvement. We present a novel inversion-specific GAN that can better distill knowledge useful for performing attacks on private models from public data. In particular, we train the discriminator to differentiate not only the real and fake samples but the soft-labels provided by the target model. Moreover, unlike previous work that directly searches for a single data point to represent a target class, we propose to model a private data distribution for each target class. Our experiments show that the combination of these techniques can significantly boost the success rate of the state-of-the-art MI attacks by 150%, and generalize better to a variety of datasets and models. Our code is available at https://github.com/SCccc21/Knowledge-Enriched-DMI.

Backdoor attacks have been considered a severe security threat to deep learning. Such attacks can make models perform abnormally on inputs with predefined triggers and still retain state-of-the-art performance on clean data. While backdoor attacks have been thoroughly investigated in the image domain from both attackers’ and defenders’ sides, an analysis in the frequency domain has been missing thus far.This paper first revisits existing backdoor triggers from a frequency perspective and performs a comprehensive analysis. Our results show that many current backdoor attacks exhibit severe high-frequency artifacts, which persist across different datasets and resolutions. We further demonstrate these high-frequency artifacts enable a simple way to detect existing backdoor triggers at a detection rate of 98.50% without prior knowledge of the attack details and the target model. Acknowledging previous attacks’ weaknesses, we propose a practical way to create smooth backdoor triggers without high-frequency artifacts and study their detectability. We show that existing defense works can benefit by incorporating these smooth triggers into their design consideration. Moreover, we show that the detector tuned over stronger smooth triggers can generalize well to unseen weak smooth triggers. In short, our work emphasizes the importance of considering frequency analysis when designing both backdoor attacks and defenses in deep learning.

Abstract Deep learning techniques have achieved remarkable performance in wide-ranging tasks. However, when trained on privacy-sensitive datasets, the model parameters may expose private information in training data. Prior attempts for differentially private training, although offering rigorous privacy guarantees, lead to much lower model performance than the non-private ones. Besides, different runs of the same training algorithm produce models with large performance variance. To address these issues, we propose DPlis– Differentially Private Learning wIth Smoothing. The core idea of DPlis is to construct a smooth loss function that favors noise-resilient models lying in large flat regions of the loss landscape. We provide theoretical justification for the utility improvements of DPlis. Extensive experiments also demonstrate that DPlis can effectively boost model quality and training stability under a given privacy budget.

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction by~\cite{fredrikson2014privacy}, such attacks have raised serious concerns given that training data usually contain privacy sensitive information. Thus far, successful model-inversion attacks have only been demonstrated on simple models, such as linear regression and logistic regression. Previous attempts to invert neural networks, even the ones with simple architectures, have failed to produce convincing results. Here we present a novel attack method, termed the \emph{generative model-inversion attack}, which can invert deep neural networks with high success rates. Rather than reconstructing private training data from scratch, we leverage partial public information, which can be very generic, to learn a distributional prior via generative adversarial networks (GANs) and use it to guide the inversion process. Moreover, we theoretically prove that a model's predictive power and its vulnerability to inversion attacks are indeed two sides of the same coin---highly predictive models are able to establish a strong correlation between features and labels, which coincides exactly with what an adversary exploits to mount the attacks. Our extensive experiments demonstrate that the proposed attack improves identification accuracy over the existing work by about $75\%$ for reconstructing face images from a state-of-the-art face recognition classifier. We also show that differential privacy, in its canonical form, is of little avail to defend against our attacks.

{\em “How much is my data worth?”} is an increasingly common question posed by organizations and individuals alike. An answer to this question could allow, for instance, fairly distributing profits among multiple data contributors and determining prospective compensation when data breaches happen. In this paper, we study the problem of \emph{data valuation} by utilizing the Shapley value, a popular notion of value which originated in coopoerative game theory. The Shapley value defines a unique payoff scheme that satisfies many desiderata for the notion of data value. However, the Shapley value often requires \emph{exponential} time to compute. To meet this challenge, we propose a repertoire of efficient algorithms for approximating the Shapley value. We also demonstrate the value of each training instance for various benchmark datasets.

Given a data set D containing millions of data points and a data consumer who is willing to pay for $ X to train a machine learning (ML) model over D , how should we distribute this $X to each data point to reflect its "value"? In this paper, we define the "relative value of data" via the Shapley value, as it uniquely possesses properties with appealing real-world interpretations, such as fairness, rationality and decentralizability. For general, bounded utility functions, the Shapley value is known to be challenging to compute: to get Shapley values for all N data points, it requires O (2 N ) model evaluations for exact computation and O ( N log N ) for ( ϵ , δ)-approximation. In this paper, we focus on one popular family of ML models relying on K -nearest neighbors ( K NN). The most surprising result is that for unweighted K NN classifiers and regressors, the Shapley value of all N data points can be computed, exactly , in O ( N log N ) time - an exponential improvement on computational complexity! Moreover, for ( ϵ , δ)-approximation, we are able to develop an algorithm based on Locality Sensitive Hashing (LSH) with only sublinear complexity O ( N h ( ϵ , K ) log N ) when ϵ is not too small and K is not too large. We empirically evaluate our algorithms on up to 10 million data points and even our exact algorithm is up to three orders of magnitude faster than the baseline approximation algorithm. The LSH-based approximation algorithm can accelerate the value calculation process even further. We then extend our algorithm to other scenarios such as (1) weighed K NN classifiers, (2) different data points are clustered by different data curators , and (3) there are data analysts providing computation who also requires proper valuation. Some of these extensions, although also being improved exponentially, are less practical for exact computation (e.g., O ( N K ) complexity for weigthed K NN). We thus propose an Monte Carlo approximation algorithm, which is O ( N (log N ) 2 /(log K ) 2 ) times more efficient than the baseline approximation algorithm.

Smart buildings today are aimed at providing safe, healthy, comfortable, affordable, and beautiful spaces in a carbon and energy-efficient way. They are emerging as complex cyber-physical systems with humans in the loop. Cost, the need to cope with increasing functional complexity, flexibility, fragmentation of the supply chain, and time-to-market pressure are rendering the traditional heuristic and ad hoc design paradigms inefficient and insufficient for the future. In this paper, we present a platform-based methodology for smart building design. Platform-based design (PBD) promotes the reuse of hardware and software on shared infrastructures, enables rapid prototyping of applications, and involves extensive exploration of the design space to optimize design performance. In this paper, we identify, abstract, and formalize components of smart buildings, and present a design flow that maps high-level specifications of desired building applications to their physical implementations under the PBD framework. A case study on the design of on-demand heating, ventilation, and air conditioning (HVAC) systems is presented to demonstrate the use of PBD.

Cyber-physical systems have enabled the collection of massive amounts of data in an unprecedented level of spatial and temporal granularity. Publishing these data can prosper big data research, which, in turn, helps improve overall system efficiency and resiliency. The main challenge in data publishing is to ensure the usefulness of published data while providing necessary privacy protection. In our previous work (Jia et al. 2017a), we presented a privacy-preserving data publishing framework (referred to as PAD hereinafter), which can guarantee k -anonymity while achieving better data utility than traditional anonymization techniques. PAD learns the information of interest to data users or features from their interactions with the data publishing system and then customizes data publishing processes to the intended use of data. However, our previous work is only applicable to the case where the desired features are linear in the original data record. In this article, we extend PAD to nonlinear features. Our experiments demonstrate that for various data-driven applications, PAD can achieve enhanced utility while remaining highly resilient to privacy threats.

Occupancy detection for buildings is crucial to improving energy efficiency, user comfort, and space utility. However, existing methods require dedicated system setup, continuous calibration, and frequent maintenance. With the instrumentation of electricity meters in millions of homes and offices, however, power measurement presents a unique opportunity for a non-intrusive and cost-effective way to detect occupant presence. This study develops solutions to the problems when no data or limited data is available for training, as motivated by difficulties in ground truth collection. Experimental evaluations on data from both residential and commercial buildings indicate that the proposed methods for binary occupancy detection are nearly as accurate as models learned with sufficient data, with accuracies of approximately 78 to 93 percent for residences and 90 percent for offices. This study shows that power usage contains valuable and sensitive user information, demonstrating a virtual occupancy sensing approach with minimal system calibration and setup.

We present results from a set of experiments in this pilot study to investigate the causal influence of user activity on various environmental parameters monitored by occupant-carried multi-purpose sensors. Hypotheses with respect to each type of measurements are verified, including temperature, humidity, and light level collected during eight typical activities: sitting in lab / cubicle, indoor walking / running, resting after physical activity, climbing stairs, taking elevators, and outdoor walking. Our main contribution is the development of features for activity and location recognition based on environmental measurements, which exploit location- and activity-specific characteristics and capture the trends resulted from the underlying physiological process. The features are statistically shown to have good separability and are also information-rich. Fusing environmental sensing together with acceleration is shown to achieve classification accuracy as high as 99.13%. For building applications, this study motivates a sensor fusion paradigm for learning individualized activity, location, and environmental preferences for energy management and user comfort.