Diffusion models are vulnerable to backdoor attacks, where malicious attackers inject backdoors by poisoning certain training samples during the training stage. This poses a significant threat to real-world applications in the Model-as-a-Service (MaaS) scenario, where users query diffusion models through APIs or directly download them from the internet. To mitigate the threat of backdoor attacks under MaaS, black-box input-level backdoor detection has drawn recent interest, where defenders aim to build a firewall that filters out backdoor samples in the inference stage, with access only to input queries and the generated results from diffusion models. Despite some preliminary explorations on the traditional classification tasks, these methods cannot be directly applied to the generative tasks due to two major challenges: (1) more diverse failures and (2) a multi-modality attack surface. In this paper, we propose a black-box input-level backdoor detection framework on diffusion models, called UFID. Our defense is motivated by an insightful causal analysis: Backdoor attacks serve as the confounder, introducing a spurious path from input to target images, which remains consistent even when we perturb the input samples with Gaussian noise. We further validate the intuition with theoretical analysis. Extensive experiments across different datasets on both conditional and unconditional diffusion models show that our method achieves superb performance on detection effectiveness and run-time efficiency.

Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack (i.e., backdoor attack) can manipulate the behavior of machine learning models through contaminating their training dataset, posing significant threat in the real-world application of large pre-trained model, especially for those customized models. Therefore, addressing the unique challenges for exploring vulnerability of pre-trained models is of paramount importance. Through empirical studies on the capability for performing backdoor attack in large pre-trained models (e.g., ViT), we find the following unique challenges of attacking large pre-trained models: 1) the inability to manipulate or even access large training datasets, and 2) the substantial computational resources required for training or fine-tuning these models. To address these challenges, we establish new standards for an effective and feasible backdoor attack in the context of large pre-trained models. In line with these standards, we introduce our EDT model, an Efficient, Data-free, Training-free backdoor attack method. Inspired by model editing techniques, EDT injects an editing-based lightweight codebook into the backdoor of large pre-trained models, which replaces the embedding of the poisoned image with the target image without poisoning the training dataset or training the victim model. Our experiments, conducted across various pre-trained models such as ViT, CLIP, BLIP, and stable diffusion, and on downstream tasks including image classification, image captioning, and image generation, demonstrate the effectiveness of our method. Our code is available at https://github.com/donglgcn/Editing/

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.

Recent studies have uncovered a troubling vulnerability in the fine-tuning stage of large language models (LLMs): even fine-tuning on entirely benign datasets can lead to a significant increase in the harmfulness of LLM outputs. Building on this finding, our red teaming study takes this threat one step further by developing a more effective attack. Specifically, we analyze and identify samples within benign datasets that contribute most to safety degradation, then fine-tune LLMs exclusively on these samples. We approach this problem from an outlier detection perspective and propose Self-Inf-N, to detect and extract outliers for fine-tuning. Our findings reveal that fine-tuning LLMs on 100 outlier samples selected by Self-Inf-N in the benign datasets severely compromises LLM safety alignment. Extensive experiments across seven mainstream LLMs demonstrate that our attack exhibits high transferability across different architectures and remains effective in practical scenarios. Alarmingly, our results indicate that most existing mitigation strategies fail to defend against this attack, underscoring the urgent need for more robust alignment safeguards. Codes are available at https://github.com/GuanZihan/Benign-Samples-Matter.

Large multi-modal models inevitably decay over time as facts update and previously learned information becomes outdated. Traditional approaches such as fine-tuning are often impractical for updating these models due to their size and complexity. Instead, direct knowledge editing within the models presents a more viable solution. Current model editing techniques, however, typically overlook the unique influence ranges of different facts, leading to compromised model performance in terms of both generality and locality. To address this issue, we introduce the concept of the generality-locality trade-off in multi-modal model editing. We develop a new model editing dataset named OKEDIT, specifically designed to effectively evaluate this trade-off. Building on this foundation, we propose BalancEdit, a novel method for balanced model editing that dynamically achieves an optimal balance between generality and locality. BalancEdit utilizes a unique mechanism that generates both positive and negative samples for each fact to accurately determine its influence scope and incorporates these insights into the model’s latent space using a discrete, localized codebook of edits, without modifying the underlying model weights. To our knowledge, this is the first approach explicitly addressing the generality-locality trade-off in multi-modal model editing. Our comprehensive results confirm the effectiveness of BalancEdit, demonstrating minimal trade-offs while maintaining robust editing capabilities. Our code and dataset are available at https://github.com/donglgcn/BalancEdit/tree/MMOKVQA.

Image segmentation is foundational to computer vision applications, and the Segment Anything Model (SAM) has become a leading base model for these tasks. However, SAM falters in specialized downstream challenges, leading to various customized SAM models. We introduce BadSAM, a backdoor attack tailored for SAM, revealing that customized models can harbor malicious behaviors. Using the CAMO dataset, we confirm BadSAM's efficacy and identify SAM vulnerabilities. This study paves the way for the development of more secure and customizable vision foundation models.

Geolocating precise locations from images presents a challenging problem in computer vision and information retrieval. Traditional methods typically employ either classification-dividing the Earth's surface into grid cells and classifying images accordingly, or retrieval-identifying locations by matching images with a database of image-location pairs. However, classification-based approaches are limited by the cell size and cannot yield precise predictions, while retrieval-based systems usually suffer from poor search quality and inadequate coverage of the global landscape at varied scale and aggregation levels. To overcome these drawbacks, we present Img2Loc, a novel system that redefines image geolocalization as a text generation task. This is achieved using cutting-edge large multi-modality models (LMMs) like GPT-4V or LLaVA with retrieval augmented generation. Img2Loc first employs CLIP-based representations to generate an image-based coordinate query database. It then uniquely combines query results with images itself, forming elaborate prompts customized for LMMs. When tested on benchmark datasets such as Im2GPS3k and YFCC4k, Img2Loc not only surpasses the performance of previous state-of-the-art models but does so without any model training. A video demonstration of the system can be accessed via this link https://drive.google.com/file/d/16A6A-mc7AyUoKHRH3_WBRToRC13sn7tU/view?usp=sharing

Backdoor attacks inject poisoned samples into training data, where backdoor triggers are embedded into the model trained on the mixture of poisoned and clean samples.An interesting phenomenon can be observed in the training process: the loss of poisoned samples tends to drop significantly faster than that of clean samples, which we call the early-fitting phenomenon.Early-fitting provides a simple but effective evidence to defend against backdoor attacks, where the poisoned samples can be detected by selecting the samples with the lowest loss values in the early training epochs.Then, two questions naturally arise: (1) What characteristics of poisoned samples cause early-fitting?(2) Does a stronger attack exist which could circumvent the defense methods?To answer the first question, we find that early-fitting could be attributed to a unique property among poisoned samples called synchronization, which depicts the similarity between two samples at different layers of a model.Meanwhile, the degree of synchronization could be controlled based on whether it is captured by shallow or deep layers of the model.Then, we give an affirmative answer to the second question by proposing a new backdoor attack method, Deep Backdoor Attack (DBA), which utilizes deep synchronization to reverse engineer trigger patterns by activating neurons in the deep layer of a base neural network.Experimental results validate our propositions and the effectiveness of DBA.Our code is available at https://github.com/GuanZihan/Deep-Backdoor-Attack.

Backdoor attacks pose a significant security risk to graph learning models. Backdoors can be embedded into the target model by inserting backdoor triggers into the training dataset, causing the model to make incorrect predictions when the trigger is present. To counter backdoor attacks, backdoor detection has been proposed. An emerging detection strategy in the vision and NLP domains is based on an intriguing phenomenon: when training models on a mixture of backdoor and clean samples, the loss on backdoor samples drops significantly faster than on clean samples, allowing backdoor samples to be easily detected by selecting samples with the lowest loss values. However, the ignorance of topological feature information on graph data limits its detection effectiveness when applied directly to the graph domain. To this end, we propose an explanation-guided backdoor detection method to take advantage of the topological information. Specifically, we train a helper model on the graph dataset, feed graph samples into the model, and then adopt explanation methods to attribute model prediction to an important subgraph. We observe that backdoor samples have distinct attribution distribution than clean samples, so the explanatory subgraph could serve as more discriminative features for detecting backdoor samples. Comprehensive experiments on multiple popular datasets and attack methods demonstrate the effectiveness and explainability of our method. Our code is available: https://github.com/GuanZihan/GNN_backdoor_detection.

Backdoor attacks inject poisoned samples into the training data, resulting in the misclassification of the poisoned input during a model's deployment. Defending against such attacks is challenging, especially for real-world black-box models where only query access is permitted. In this paper, we propose a novel defense framework against backdoor attacks through Zero-shot Image Purification (ZIP). Our framework can be applied to poisoned models without requiring internal information about the model or any prior knowledge of the clean/poisoned samples. Our defense framework involves two steps. First, we apply a linear transformation (e.g., blurring) on the poisoned image to destroy the backdoor pattern. Then, we use a pre-trained diffusion model to recover the missing semantic information removed by the transformation. In particular, we design a new reverse process by using the transformed image to guide the generation of high-fidelity purified images, which works in zero-shot settings. We evaluate our ZIP framework on multiple datasets with different types of attacks. Experimental results demonstrate the superiority of our ZIP framework compared to state-of-the-art backdoor defense baselines. We believe that our results will provide valuable insights for future defense methods for black-box models. Our code is available at https://github.com/sycny/ZIP.