NeurIPS 2024 论文列表

While Large Language Models (LLMs) display versatile functionality, they continue to generate harmful, biased, and toxic content, as demonstrated by the prevalence of human-designed *jailbreaks*. In this work, we present *Tree of Attacks with Pruning* (TAP), an automated method for generating jailbreaks that only requires black-box access to the target LLM. TAP utilizes an attacker LLM to iteratively refine candidate (attack) prompts until one of the refined prompts jailbreaks the target. In addition, before sending prompts to the target, TAP assesses them and prunes the ones unlikely to result in jailbreaks, reducing the number of queries sent to the target LLM. In empirical evaluations, we observe that TAP generates prompts that jailbreak state-of-the-art LLMs (including GPT4-Turbo and GPT4o) for more than 80% of the prompts. This significantly improves upon the previous state-of-the-art black-box methods for generating jailbreaks while using a smaller number of queries than them. Furthermore, TAP is also capable of jailbreaking LLMs protected by state-of-the-art *guardrails*, e.g., LlamaGuard.

Visible-infrared person re-identification (VIReID) is widely used in fields such as video surveillance and intelligent transportation, imposing higher demands on model security. In practice, the adversarial attacks based on VIReID aim to disrupt output ranking and quantify the security risks of models. Although numerous studies have been emerged on adversarial attacks and defenses in fields such as face recognition, person re-identification, and pedestrian detection, there is currently a lack of research on the security of VIReID systems. To this end, we propose to explore the vulnerabilities of VIReID systems and prevent potential serious losses due to insecurity. Compared to research on single-modality ReID, adversarial feature alignment and modality differences need to be particularly emphasized. Thus, we advocate for feature-level adversarial attacks to disrupt the output rankings of VIReID systems. To obtain adversarial features, we introduce \textit{Universal Adversarial Perturbations} (UAP) to simulate common disturbances in real-world environments. Additionally, we employ a \textit{Frequency-Spatial Attention Module} (FSAM), integrating frequency information extraction and spatial focusing mechanisms, and further emphasize important regional features from different domains on the shared features. This ensures that adversarial features maintain consistency within the feature space. Finally, we employ an \textit{Auxiliary Quadruple Adversarial Loss} to amplify the differences between modalities, thereby improving the distinction and recognition of features between visible and infrared images, which causes the system to output incorrect rankings. Extensive experiments on two VIReID benchmarks (i.e., SYSU-MM01, RegDB) and different systems validate the effectiveness of our method.

Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not. Existing MIAs designed for large language models (LLMs) can be bifurcated into two types: reference-free and reference-based attacks. Although reference-based attacks appear promising performance by calibrating the probability measured on the target model with reference models, this illusion of privacy risk heavily depends on a reference dataset that closely resembles the training set. Both two types of attacks are predicated on the hypothesis that training records consistently maintain a higher probability of being sampled. However, this hypothesis heavily relies on the overfitting of target models, which will be mitigated by multiple regularization methods and the generalization of LLMs. Thus, these reasons lead to high false-positive rates of MIAs in practical scenarios. We propose a Membership Inference Attack based on Self-calibrated Probabilistic Variation (SPV-MIA). Specifically, we introduce a self-prompt approach, which constructs the dataset to fine-tune the reference model by prompting the target LLM itself. In this manner, the adversary can collect a dataset with a similar distribution from public APIs. Furthermore, we introduce probabilistic variation, a more reliable membership signal based on LLM memorization rather than overfitting, from which we rediscover the neighbour attack with theoretical grounding. Comprehensive evaluation conducted on three datasets and four exemplary LLMs shows that SPV-MIA raises the AUC of MIAs from 0.7 to a significantly high level of 0.9. Our code and dataset are available at: https://github.com/tsinghua-fib-lab/NeurIPS2024_SPV-MIA

Driven by the rapid development of Large Language Models (LLMs), LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and security of LLM-based agents during applications. However, the safety issues of LLM-based agents are currently under-explored. In this work, we take the first step to investigate one of the typical safety threats, backdoor attack, to LLM-based agents. We first formulate a general framework of agent backdoor attacks, then we present a thorough analysis of different forms of agent backdoor attacks. Specifically, compared with traditional backdoor attacks on LLMs that are only able to manipulate the user inputs and model outputs, agent backdoor attacks exhibit more diverse and covert forms: (1) From the perspective of the final attacking outcomes, the agent backdoor attacker can not only choose to manipulate the final output distribution, but also introduce the malicious behavior in an intermediate reasoning step only, while keeping the final output correct. (2) Furthermore, the former category can be divided into two subcategories based on trigger locations, in which the backdoor trigger can either be hidden in the user query or appear in an intermediate observation returned by the external environment. We implement the above variations of agent backdoor attacks on two typical agent tasks including web shopping and tool utilization. Extensive experiments show that LLM-based agents suffer severely from backdoor attacks and such backdoor vulnerability cannot be easily mitigated by current textual backdoor defense algorithms. This indicates an urgent need for further research on the development of targeted defenses against backdoor attacks on LLM-based agents. Warning: This paper may contain biased content.

It is well known that query-based attacks tend to have relatively higher success rates in adversarial black-box attacks. While research on black-box attacks is actively being conducted, relatively few studies have focused on pixel attacks that target only a limited number of pixels. In image classification, query-based pixel attacks often rely on patches, which heavily depend on randomness and neglect the fact that scattered pixels are more suitable for adversarial attacks. Moreover, to the best of our knowledge, query-based pixel attacks have not been explored in the field of object detection. To address these issues, we propose a novel pixel-based black-box attack called Remember and Forget Pixel Attack using Reinforcement Learning(RFPAR), consisting of two main components: the Remember and Forget processes. RFPAR mitigates randomness and avoids patch dependency by leveraging rewards generated through a one-step RL algorithm to perturb pixels. RFPAR effectively creates perturbed images that minimize the confidence scores while adhering to limited pixel constraints. Furthermore, we advance our proposed attack beyond image classification to object detection, where RFPAR reduces the confidence scores of detected objects to avoid detection. Experiments on the ImageNet-1K dataset for classification show that RFPAR outperformed state-of-the-art query-based pixel attacks. For object detection, using the MSCOCO dataset with YOLOv8 and DDQ, RFPAR demonstrates comparable mAP reduction to state-of-the-art query-based attack while requiring fewer query. Further experiments on the Argoverse dataset using YOLOv8 confirm that RFPAR effectively removed objects on a larger scale dataset. Our code is available at https://github.com/KAU-QuantumAILab/RFPAR.

The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense. Additionally, vanilla fine-tuning with those clean data can help recover the lost clean accuracy. However, the behavior of clean unlearning is still under-explored, and vanilla fine-tuning unintentionally induces back the backdoor effect. In this work, we first investigate model unlearning from the perspective of weight changes and gradient norms, and find two interesting observations in the backdoored model: 1) the weight changes between poison and clean unlearning are positively correlated, making it possible for us to identify the backdoored-related neurons without using poisoned data; 2) the neurons of the backdoored model are more active (*i.e.*, larger gradient norm) than those in the clean model, suggesting the need to suppress the gradient norm during fine-tuning. Then, we propose an effective two-stage defense method. In the first stage, an efficient *Neuron Weight Change (NWC)-based Backdoor Reinitialization* is proposed based on observation 1). In the second stage, based on observation 2), we design an *Activeness-Aware Fine-Tuning* to replace the vanilla fine-tuning. Extensive experiments, involving eight backdoor attacks on three benchmark datasets, demonstrate the superior performance of our proposed method compared to recent state-of-the-art backdoor defense approaches. The code is available at https://github.com/linweiii/TSBD.git.

Multivariate Time Series (MTS) forecasting is a fundamental task with numerous real-world applications, such as transportation, climate, and epidemiology. While a myriad of powerful deep learning models have been developed for this task, few works have explored the robustness of MTS forecasting models to malicious attacks, which is crucial for their trustworthy employment in high-stake scenarios. To address this gap, we dive deep into the backdoor attacks on MTS forecasting models and propose an effective attack method named BackTime. By subtly injecting a few \textit{stealthy triggers} into the MTS data, BackTime can alter the predictions of the forecasting model according to the attacker's intent. Specifically, BackTime first identifies vulnerable timestamps in the data for poisoning, and then adaptively synthesizes stealthy and effective triggers by solving a bi-level optimization problem with a GNN-based trigger generator. Extensive experiments across multiple datasets and state-of-the-art MTS forecasting models demonstrate the effectiveness, versatility, and stealthiness of BackTime attacks.

Due to the increasing popularity of Artificial Intelligence (AI), more and more backdoor attacks are designed to mislead Deep Neural Network (DNN) predictions by manipulating training samples or processes. Although backdoor attacks have been investigated in various scenarios, they still suffer from the problems of both low fidelity of poisoned samples and non-negligible transfer in latent space, which make them easily identified by existing backdoor detection algorithms. To overcome this weakness, this paper proposes a novel frequency-based backdoor attack method named WaveAttack, which obtains high-frequency image features through Discrete Wavelet Transform (DWT) to generate highly stealthy backdoor triggers. By introducing an asymmetric frequency obfuscation method, our approach adds an adaptive residual to the training and inference stages to improve the impact of triggers, thus further enhancing the effectiveness of WaveAttack. Comprehensive experimental results show that, WaveAttack can not only achieve higher effectiveness than state-of-the-art backdoor attack methods, but also outperform them in the fidelity of images (i.e., by up to 28.27\% improvement in PSNR, 1.61\% improvement in SSIM, and 70.59\% reduction in IS). Our code is available at https://github.com/BililiCode/WaveAttack.

Reinforcement learning (RL) is an actively growing field that is seeing increased usage in real-world, safety-critical applications -- making it paramount to ensure the robustness of RL algorithms against adversarial attacks. In this work we explore a particularly stealthy form of training-time attacks against RL -- backdoor poisoning. Here the adversary intercepts the training of an RL agent with the goal of reliably inducing a particular action when the agent observes a pre-determined trigger at inference time. We uncover theoretical limitations of prior work by proving their inability to generalize across domains and MDPs. Motivated by this, we formulate a novel poisoning attack framework which interlinks the adversary's objectives with those of finding an optimal policy -- guaranteeing attack success in the limit. Using insights from our theoretical analysis we develop "SleeperNets" as a universal backdoor attack which exploits a newly proposed threat model and leverages dynamic reward poisoning techniques. We evaluate our attack in 6 environments spanning multiple domains and demonstrate significant improvements in attack success over existing methods, while preserving benign episodic return.

Model Inversion (MI) attacks pose a significant threat to the privacy of Deep Neural Networks by recovering training data distribution from well-trained models. While existing defenses often rely on regularization techniques to reduce information leakage, they remain vulnerable to recent attacks. In this paper, we propose the Trapdoor-based Model Inversion Defense (Trap-MID) to mislead MI attacks. A trapdoor is integrated into the model to predict a specific label when the input is injected with the corresponding trigger. Consequently, this trapdoor information serves as the "shortcut" for MI attacks, leading them to extract trapdoor triggers rather than private data. We provide theoretical insights into the impacts of trapdoor's effectiveness and naturalness on deceiving MI attacks. In addition, empirical experiments demonstrate the state-of-the-art defense performance of Trap-MID against various MI attacks without the requirements for extra data or large computational overhead. Our source code is publicly available at https://github.com/ntuaislab/Trap-MID.

Availability attacks provide a tool to prevent the unauthorized use of private data and commercial datasets by generating imperceptible noise and crafting unlearnable examples before release. Ideally, the obtained unlearnability can prevent algorithms from training usable models. When supervised learning (SL) algorithms have failed, a malicious data collector possibly resorts to contrastive learning (CL) algorithms to bypass the protection. Through evaluation, we have found that most existing methods are unable to achieve both supervised and contrastive unlearnability, which poses risks to data protection by availability attacks. Different from recent methods based on contrastive learning, we employ contrastive-like data augmentations in supervised learning frameworks to obtain attacks effective for both SL and CL. Our proposed AUE and AAP attacks achieve state-of-the-art worst-case unlearnability across SL and CL algorithms with less computation consumption, showcasing prospects in real-world applications. The code is available at https://github.com/EhanW/AUE-AAP.

Deep neural networks face persistent challenges in defending against backdoor attacks, leading to an ongoing battle between attacks and defenses. While existing backdoor defense strategies have shown promising performance on reducing attack success rates, can we confidently claim that the backdoor threat has truly been eliminated from the model? To address it, we re-investigate the characteristics of the backdoored models after defense (denoted as defense models). Surprisingly, we find that the original backdoors still exist in defense models derived from existing post-training defense strategies, and the backdoor existence is measured by a novel metric called backdoor existence coefficient. It implies that the backdoors just lie dormant rather than being eliminated. To further verify this finding, we empirically show that these dormant backdoors can be easily re-activated during inference stage, by manipulating the original trigger with well-designed tiny perturbation using universal adversarial attack. More practically, we extend our backdoor re-activation to black-box scenario, where the defense model can only be queried by the adversary during inference stage, and develop two effective methods, i.e., query-based and transfer-based backdoor re-activation attacks. The effectiveness of the proposed methods are verified on both image classification and multimodal contrastive learning (i.e., CLIP) tasks. In conclusion, this work uncovers a critical vulnerability that has never been explored in existing defense strategies, emphasizing the urgency of designing more robust and advanced backdoor defense mechanisms in the future.

Physical adversarial attacks can deceive deep neural networks (DNNs), leading to erroneous predictions in real-world scenarios. To uncover potential security risks, attacking the safety-critical task of person detection has garnered significant attention. However, we observe that existing attack methods overlook the pivotal role of the camera, involving capturing real-world scenes and converting them into digital images, in the physical adversarial attack workflow. This oversight leads to instability and challenges in reproducing these attacks. In this work, we revisit patch-based attacks against person detectors and introduce a camera-agnostic physical adversarial attack to mitigate this limitation. Specifically, we construct a differentiable camera Image Signal Processing (ISP) proxy network to compensate for the physical-to-digital transition gap. Furthermore, the camera ISP proxy network serves as a defense module, forming an adversarial optimization framework with the attack module. The attack module optimizes adversarial patches to maximize effectiveness, while the defense module optimizes the conditional parameters of the camera ISP proxy network to minimize attack effectiveness. These modules engage in an adversarial game, enhancing cross-camera stability. Experimental results demonstrate that our proposed Camera-Agnostic Patch (CAP) attack effectively conceals persons from detectors across various imaging hardware, including two distinct cameras and four smartphones.

Despite the general capabilities of Large Language Models (LLMs) like GPT-4, these models still request fine-tuning or adaptation with customized data when meeting the specific business demands and intricacies of tailored use cases. However, this process inevitably introduces new safety threats, particularly against the Fine-tuning based Jailbreak Attack (FJAttack) under the setting of Language-Model-as-a-Service (LMaaS), where the model's safety has been significantly compromised by fine-tuning on users' uploaded examples that contain just a few harmful examples. Though potential defenses have been proposed that the service providers of LMaaS can integrate safety examples into the fine-tuning dataset to reduce safety issues, such approaches require incorporating a substantial amount of data, making it inefficient. To effectively defend against the FJAttack with limited safety examples under LMaaS, we propose the Backdoor Enhanced Safety Alignment method inspired by an analogy with the concept of backdoor attacks. In particular, service providers will construct prefixed safety examples with a secret prompt, acting as a "backdoor trigger". By integrating prefixed safety examples into the fine-tuning dataset, the subsequent fine-tuning process effectively acts as the "backdoor attack", establishing a strong correlation between the secret prompt and safety generations. Consequently, safe responses are ensured once service providers prepend this secret prompt ahead of any user input during inference. Our comprehensive experiments demonstrate that through the Backdoor Enhanced Safety Alignment with adding as few as 11 prefixed safety examples, the maliciously fine-tuned LLMs will achieve similar safety performance as the original aligned models without harming the benign performance. Furthermore, we also present the effectiveness of our method in a more practical setting where the fine-tuning data consists of both FJAttack examples and the fine-tuning task data.