Enhancing privacy on smart contract-enabled blockchains has garnered much attention in recent research. Zero-knowledge proofs (ZKPs) is one of the most popular approaches, however, they fail to provide full expressiveness and fine-grained privacy. To illustrate this, we underscore an underexplored type of Miner Extractable Value (MEV), called Residual Bids Extractable Value (RBEV). Residual bids highlight the vulnerability where unfulfilled bids inadvertently reveal traders' unmet demands and prospective trading strategies, thus exposing them to exploitation. ZKP-based approaches failed to address RBEV as they cannot provide post-execution privacy without some level of information disclosure. Other MEV mitigations like fair-ordering protocols also failed to address RBEV. We introduce Ratel, an innovative framework bridging a multi-party computation (MPC) prototyping framework (MP-SPDZ) and a smart contract language (Solidity), harmonizing the privacy with full expressiveness of MPC with Solidity 's on-chain programmability. This synergy empowers developers to effortlessly craft privacy-preserving decentralized applications (DApps). We demonstrate Ratel's efficacy through two distinguished decentralized finance (DeFi) applications: a decentralized exchange and a collateral auction, effectively mitigating the potential RBEV issue. Furthermore, Ratel is equipped with a lightweight crash-reset mechanism, enabling the seamless recovery of transiently benign faulty nodes. To prevent the crash-reset mechanism abused by malicious entities and ward off DoS attacks, we incorporate a cost-utility analysis anchored in the Bayesian approach. Our performance evaluation of the applications developed under the Ratel framework underscores their competency in managing real-world peak-time workloads.

Researchers across various fields seek to understand causal relationships but often find controlled experiments impractical. To address this, statistical tools for causal discovery from naturally observed data have become crucial. Non-linear regression models, such as Gaussian process regression, are commonly used in causal inference but have limitations due to high costs when adapted for secure computation. Support vector regression (SVR) offers an alternative but remains costly in an Multi-party computation context due to conditional branches and support vector updates.

Speech models are often trained on sensitive data in order to improve model performance, leading to potential privacy leakage. Our work considers noise masking attacks, introduced by Amid et al. [1], which attack automatic speech recognition (ASR) models by requesting a transcript of an utterance which is partially replaced with noise. They show that when a record has been seen at training time, the model will transcribe the noisy record with its memorized sensitive transcript. In our work, we extend these attacks beyond ASR models, to attack pretrained speech encoders. Our method fine-tunes the encoder to produce an ASR model, and then performs noise masking on this model, which we find recovers private information from the pretraining data, despite the model never having seen transcripts at pretraining time! We show how to improve the precision of these attacks and investigate a number of countermeasures to our attacks.

It is well-known that neural networks can unintentionally memorize their training examples, causing privacy concerns. However, auditing memorization in large non-auto-regressive automatic speech recognition (ASR) models has been challenging due to the high compute cost of existing methods such as hardness calibration. In this work, we design a simple auditing method to measure memorization in large ASR models without the extra compute overhead. Concretely, we speed up randomly-generated utterances to create a mapping between vocal and text information that is difficult to learn from typical training examples. Hence, accurate predictions only for sped-up training examples can serve as clear evidence for memorization, and the corresponding accuracy can be used to measure memorization. Using the proposed method, we showcase memorization in the state-of-the-art ASR models. To mitigate memorization, we tried gradient clipping during training to bound the influence of any individual example on the final model. We empirically show that clipping each example’s gradient can mitigate memorization for sped-up training examples with up to 16 repetitions in the training set. Furthermore, we show that in large-scale distributed training, clipping the average gradient on each compute core maintains neutral model quality and compute cost while providing strong privacy protection.

We propose Byzantine-robust federated learning protocols with nearly optimal statistical rates based on recent progress in high dimensional robust statistics. In contrast to prior work, our proposed protocols improve the dimension dependence and achieve a near-optimal statistical rate for strongly convex losses. We also provide statistical lower bound for the problem. For experiments, we benchmark against competing protocols and show the empirical superiority of the proposed protocols.

In the privacy-utility tradeoff of a model trained on benchmark language and vision tasks, remarkable improvements have been widely reported when the model is pretrained on public data. Some gain is expected as these models inherit the benefits of transfer learning, which is the standard motivation in non-private settings. However, the stark contrast in the gain of pretraining between non-private and private machine learning suggests that the gain in the latter is rooted in a fundamentally different cause. To explain this phenomenon, we hypothesize that the non-convex loss landscape of a model training necessitates the optimization algorithm to go through two phases. In the first, the algorithm needs to select a good “basin” in the loss landscape. In the second, the algorithm solves an easy optimization within that basin. The former is a harder problem to solve with private data, while the latter is harder to solve with public data due to a distribution shift or data scarcity. Guided by this intuition, we provide theoretical constructions that provably demonstrate the separation between private training with and without public pretraining. Further, systematic experiments on CIFAR10 and Librispeech provide supporting evidence for our hypothesis.

We propose the first federated correlation test framework compatible with secure aggregation, namely FED-$\chi^2$. In our protocol, the statistical computations are recast as frequency moment estimation problems, where the clients collaboratively generate a shared projection matrix and then use stable projection to encode the local information in a compact vector. As such encodings can be linearly aggregated, secure aggregation can be applied to conceal the individual updates. We formally establish the security guarantee of FED-$\chi^2$ by proving that only the minimum necessary information (i.e., the correlation statistics) is revealed to the server. We show that our protocol can be naturally extended to estimate other statistics that can be recast as frequency moment estimations. By accommodating Shannon’e Entropy in FED-$\chi^2$, we further propose the first secure federated entropy estimation protocol, FED-$H$. The evaluation results demonstrate that FED-$\chi^2$ and FED-$H$ achieve good performance with small client-side computation overhead in several real-world case studies.

The Sketch is a compact data structure useful for network measurements. However, to cope with the high speeds of the current data plane, it needs to be held in the small on-chip memory (SRAM). Therefore, the product of the counter size and the number of counters must be below a certain limit. With small counters, some will overflow. With large counters, the total number of counters will be small, but each counter will be shared by more flows, leading to poor accuracy. To address this issue, we propose a generic technique:self-adaptive counters (SEAD Counter). When the value of the counter is small, it works as a standard counter. When the value of the counter is large however, we increment it using a predefined probability, so as to represent this large value. Moreover, in the SEAD Counter, the probability decreases when the value increases. We show that this technique can significantly improve the accuracy of counters. This technique can be adapted to different circumstances. We theoretically analyze the improvements achieved by the SEAD Counter. We further show that our SEAD Counter can be extended to three typical sketches and Bloom filters. We conduct extensive experiments on three real datasets and one synthetic dataset. The experimental results show that, compared with the state-of-the-art, sketches using the SEAD Counter improve the accuracy by up to 13.6 times, while the Bloom filters using SEAD Counter can reduce the false positive rate by more than one order of magnitude.

Recent research has confirmed the feasibility of backdoor attacks in deep reinforcement learning (RL) systems. However, the existing attacks require the ability to arbitrarily modify an agent's observation, constraining the application scope to simple RL systems such as Atari games. In this paper, we migrate backdoor attacks to more complex RL systems involving multiple agents and explore the possibility of triggering the backdoor without directly manipulating the agent's observation. As a proof of concept, we demonstrate that an adversary agent can trigger the backdoor of the victim agent with its own action in two-player competitive RL systems. We prototype and evaluate BackdooRL in four competitive environments. The results show that when the backdoor is activated, the winning rate of the victim drops by 17% to 37% compared to when not activated. The videos are hosted at https://github.com/wanglun1996/multi_agent_rl_backdoor_videos.

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.

A trojan backdoor is a hidden pattern typically implanted in a deep neural network (DNN). It could be activated and thus forces that infected model to behave abnormally when an input sample with a particular trigger is fed to that model. As such, given a DNN and clean input samples, it is challenging to inspect and determine the existence of a trojan backdoor. Recently, researchers design and develop several pioneering solutions to address this problem. They demonstrate that the proposed techniques have great potential in trojan detection. However, we show that none of these existing techniques completely address the problem. On the one hand, they mostly work under an unrealistic assumption of assuming the availability of the contaminated training database. On the other hand, these techniques can neither accurately detect the existence of trojan backdoors, nor restore high-fidelity triggers, especially when infected models are trained with high-dimensional data, and the triggers pertaining to the trojan vary in size, shape, and position. In this work, we propose TABOR, a new trojan detection technique. Conceptually, it formalizes the detection of a trojan backdoor as solving an optimization objective function. Different from the existing technique which also models trojan detection as an optimization problem, TABOR first designs a new objective function that could guide optimization to identify a trojan backdoor more correctly and accurately. Second, TABOR borrows the idea of interpretable AI to further prune the restored triggers. Last, TABOR designs a new anomaly detection method, which could not only facilitate the identification of intentionally injected triggers but also filter out false alarms (i.e., triggers detected from an uninfected model). We train 112 DNNs on five datasets and infect these models with two existing trojan attacks. We evaluate TABOR by using these infected models, and demonstrate that TABOR has much better performance in trigger restoration, trojan detection, and elimination than Neural Cleanse, the state-of-the-art trojan detection technique.

Causal graph discovery refers to the process of discovering causal relation graphs from purely observational data. Like other statistical data, a causal graph might leak sensitive information about participants in the dataset. In this paper, we present a differentially private causal graph discovery algorithm, Priv-PC, which improves both utility and running time compared to the state-of-the-art. The design of Priv-PC follows a novel paradigm called sieve-and-examine which uses a small amount of privacy budget to filter out “insignificant” queries, and leverages the remaining budget to obtain highly accurate answers for the “significant” queries. We also conducted the first sensitivity analysis for conditional independence tests including conditional Kendall’s τ and conditional Spearman’s ρ. We evaluated Priv-PC on 7 public datasets and compared with the state-of-the-art. The results show that Priv-PC achieves 10.61 to 293.87 times speedup and better utility. The implementation of Priv-PC, including the code used in our evaluation, is available at https://github.com/sunblaze-ucb/ Priv-PC-Differentially-Private-Causal-Graph-Discovery.

We introduce CHURP (CHUrn-Robust Proactive secret sharing). CHURP enables secure secret-sharing in dynamic settings, where the committee of nodes storing a secret changes over time. Designed for blockchains, CHURP has lower communication complexity than previous schemes: $O(n)$ on-chain and $O(n^2)$ off-chain in the optimistic case of no node failures. CHURP includes several technical innovations: An efficient new proactivization scheme of independent interest, a technique (using asymmetric bivariate polynomials) for efficiently changing secret-sharing thresholds, and a hedge against setup failures in an efficient polynomial commitment scheme. We also introduce a general new technique for inexpensive off-chain communication across the peer-to-peer networks of permissionless blockchains. We formally prove the security of CHURP, report on an implementation, and present performance measurements.

Sketch is a compact data structure for network measurements. To achieve fast speed, it needs to be held in the on-chip memory (SRAM), which is very small. To enable the sketch fit into the on-chip memory, the product of counter size and number of counters must be below a certain limit. If we use small counters, e.g., 8 bits, some counters will overflow. If we use large counters, e.g., 16 bits per counter, the total number of counters will be small, each counter will be shared by more flows, leading to poor accuracy. To address this issue, we propose a generic technique: self-adaptive counters (SA Counter). When the value of the counter is small, it works as a normal counter. When the value of the counter is large, we increment it using a predefined probability, so as to represent a large value. Moreover, in SA Counter, the probability decreases when the value increases. This technique can significantly improve the accuracy of sketches. To verify the effectiveness of SA Counter, we apply SA Counter to three typical sketches, and conduct extensive experiments on one real dataset and one synthetic dataset. Experimental results show that, compared with the state-of-the-art, sketches using SA Counter improve the accuracy by up to 13.6 times.

Building useful predictive models often involves learning from sensitive data. Training models with differential privacy can guarantee the privacy of such sensitive data. For convex optimization tasks, several differentially private algorithms are known, but none has yet been deployed in practice. In this work, we make two major contributions towards practical differentially private convex optimization. First, we present Approximate Minima Perturbation, a novel algorithm that can leverage any off-the-shelf optimizer. We show that it can be employed without any hyperparameter tuning, thus making it an attractive technique for practical deployment. Second, we perform an extensive empirical evaluation of the state-of-the-art algorithms for differentially private convex optimization, on a range of publicly available benchmark datasets, and real-world datasets obtained through an industrial collaboration. We release open-source implementations of all the differentially private convex optimization algorithms considered, and benchmarks on as many as nine public datasets, four of which are high-dimensional.

During the past decade, differential privacy has become the gold standard for protecting the privacy of individuals. However, verifying that a particular program provides differential privacy often remains a manual task to be completed by an expert in the field. Language-based techniques have been proposed for fully automating proofs of differential privacy via type system design, however these results have lagged behind advances in differentially-private algorithms, leaving a noticeable gap in programs which can be automatically verified while also providing state-of-the-art bounds on privacy. We propose Duet, an expressive higher-order language, linear type system and tool for automatically verifying differential privacy of general-purpose higher-order programs. In addition to general purpose programming, Duet supports encoding machine learning algorithms such as stochastic gradient descent, as well as common auxiliary data analysis tasks such as clipping, normalization and hyperparameter tuning - each of which are particularly challenging to encode in a statically verified differential privacy framework. We present a core design of the Duet language and linear type system, and complete key proofs about privacy for well-typed programs. We then show how to extend Duet to support realistic machine learning applications and recent variants of differential privacy which result in improved accuracy for many practical differentially private algorithms. Finally, we implement several differentially private machine learning algorithms in Duet which have never before been automatically verified by a language-based tool, and we present experimental results which demonstrate the benefits of Duet's language design in terms of accuracy of trained machine learning models.