Abstract:Large Vision-Language Models (LVLMs) have been widely adopted in various applications; however, they exhibit significant gender biases. Existing benchmarks primarily evaluate gender bias at the demographic group level, neglecting individual fairness, which emphasizes equal treatment of similar individuals. This research gap limits the detection of discriminatory behaviors, as individual fairness offers a more granular examination of biases that group fairness may overlook. For the first time, this paper introduces the GenderBias-\emph{VL} benchmark to evaluate occupation-related gender bias in LVLMs using counterfactual visual questions under individual fairness criteria. To construct this benchmark, we first utilize text-to-image diffusion models to generate occupation images and their gender counterfactuals. Subsequently, we generate corresponding textual occupation options by identifying stereotyped occupation pairs with high semantic similarity but opposite gender proportions in real-world statistics. This method enables the creation of large-scale visual question counterfactuals to expose biases in LVLMs, applicable in both multimodal and unimodal contexts through modifying gender attributes in specific modalities. Overall, our GenderBias-\emph{VL} benchmark comprises 34,581 visual question counterfactual pairs, covering 177 occupations. Using our benchmark, we extensively evaluate 15 commonly used open-source LVLMs (\eg, LLaVA) and state-of-the-art commercial APIs, including GPT-4o and Gemini-Pro. Our findings reveal widespread gender biases in existing LVLMs. Our benchmark offers: (1) a comprehensive dataset for occupation-related gender bias evaluation; (2) an up-to-date leaderboard on LVLM biases; and (3) a nuanced understanding of the biases presented by these models. \footnote{The dataset and code are available at the \href{https://genderbiasvl.github.io/}{website}.}
Abstract:Instruction tuning enhances large vision-language models (LVLMs) but raises security risks through potential backdoor attacks due to their openness. Previous backdoor studies focus on enclosed scenarios with consistent training and testing instructions, neglecting the practical domain gaps that could affect attack effectiveness. This paper empirically examines the generalizability of backdoor attacks during the instruction tuning of LVLMs for the first time, revealing certain limitations of most backdoor strategies in practical scenarios. We quantitatively evaluate the generalizability of six typical backdoor attacks on image caption benchmarks across multiple LVLMs, considering both visual and textual domain offsets. Our findings indicate that attack generalizability is positively correlated with the backdoor trigger's irrelevance to specific images/models and the preferential correlation of the trigger pattern. Additionally, we modify existing backdoor attacks based on the above key observations, demonstrating significant improvements in cross-domain scenario generalizability (+86% attack success rate). Notably, even without access to the instruction datasets, a multimodal instruction set can be successfully poisoned with a very low poisoning rate (0.2%), achieving an attack success rate of over 97%. This paper underscores that even simple traditional backdoor strategies pose a serious threat to LVLMs, necessitating more attention and in-depth research.
Abstract:The recent release of GPT-4o has garnered widespread attention due to its powerful general capabilities. While its impressive performance is widely acknowledged, its safety aspects have not been sufficiently explored. Given the potential societal impact of risky content generated by advanced generative AI such as GPT-4o, it is crucial to rigorously evaluate its safety. In response to this question, this paper for the first time conducts a rigorous evaluation of GPT-4o against jailbreak attacks. Specifically, this paper adopts a series of multi-modal and uni-modal jailbreak attacks on 4 commonly used benchmarks encompassing three modalities (\ie, text, speech, and image), which involves the optimization of over 4,000 initial text queries and the analysis and statistical evaluation of nearly 8,000+ response on GPT-4o. Our extensive experiments reveal several novel observations: (1) In contrast to the previous version (such as GPT-4V), GPT-4o has enhanced safety in the context of text modality jailbreak; (2) The newly introduced audio modality opens up new attack vectors for jailbreak attacks on GPT-4o; (3) Existing black-box multimodal jailbreak attack methods are largely ineffective against GPT-4o and GPT-4V. These findings provide critical insights into the safety implications of GPT-4o and underscore the need for robust alignment guardrails in large models. Our code is available at \url{https://github.com/NY1024/Jailbreak_GPT4o}.
Abstract:In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks predominantly focus on the visual modality, perturbing solely visual inputs in the prompt for attacks. However, they fall short when confronted with aligned models that fuse visual and textual features simultaneously for generation. To address this limitation, this paper introduces the Bi-Modal Adversarial Prompt Attack (BAP), which executes jailbreaks by optimizing textual and visual prompts cohesively. Initially, we adversarially embed universally harmful perturbations in an image, guided by a few-shot query-agnostic corpus (e.g., affirmative prefixes and negative inhibitions). This process ensures that image prompt LVLMs to respond positively to any harmful queries. Subsequently, leveraging the adversarial image, we optimize textual prompts with specific harmful intent. In particular, we utilize a large language model to analyze jailbreak failures and employ chain-of-thought reasoning to refine textual prompts through a feedback-iteration manner. To validate the efficacy of our approach, we conducted extensive evaluations on various datasets and LVLMs, demonstrating that our method significantly outperforms other methods by large margins (+29.03% in attack success rate on average). Additionally, we showcase the potential of our attacks on black-box commercial LVLMs, such as Gemini and ChatGLM.
Abstract:Lane detection (LD) is an essential component of autonomous driving systems, providing fundamental functionalities like adaptive cruise control and automated lane centering. Existing LD benchmarks primarily focus on evaluating common cases, neglecting the robustness of LD models against environmental illusions such as shadows and tire marks on the road. This research gap poses significant safety challenges since these illusions exist naturally in real-world traffic situations. For the first time, this paper studies the potential threats caused by these environmental illusions to LD and establishes the first comprehensive benchmark LanEvil for evaluating the robustness of LD against this natural corruption. We systematically design 14 prevalent yet critical types of environmental illusions (e.g., shadow, reflection) that cover a wide spectrum of real-world influencing factors in LD tasks. Based on real-world environments, we create 94 realistic and customizable 3D cases using the widely used CARLA simulator, resulting in a dataset comprising 90,292 sampled images. Through extensive experiments, we benchmark the robustness of popular LD methods using LanEvil, revealing substantial performance degradation (-5.37% Accuracy and -10.70% F1-Score on average), with shadow effects posing the greatest risk (-7.39% Accuracy). Additionally, we assess the performance of commercial auto-driving systems OpenPilot and Apollo through collaborative simulations, demonstrating that proposed environmental illusions can lead to incorrect decisions and potential traffic accidents. To defend against environmental illusions, we propose the Attention Area Mixing (AAM) approach using hard examples, which witness significant robustness improvement (+3.76%) under illumination effects. We hope our paper can contribute to advancing more robust auto-driving systems in the future. Website: https://lanevil.github.io/.
Abstract:Vision-Large-Language-Models (Vision-LLMs) are increasingly being integrated into autonomous driving (AD) systems due to their advanced visual-language reasoning capabilities, targeting the perception, prediction, planning, and control mechanisms. However, Vision-LLMs have demonstrated susceptibilities against various types of adversarial attacks, which would compromise their reliability and safety. To further explore the risk in AD systems and the transferability of practical threats, we propose to leverage typographic attacks against AD systems relying on the decision-making capabilities of Vision-LLMs. Different from the few existing works developing general datasets of typographic attacks, this paper focuses on realistic traffic scenarios where these attacks can be deployed, on their potential effects on the decision-making autonomy, and on the practical ways in which these attacks can be physically presented. To achieve the above goals, we first propose a dataset-agnostic framework for automatically generating false answers that can mislead Vision-LLMs' reasoning. Then, we present a linguistic augmentation scheme that facilitates attacks at image-level and region-level reasoning, and we extend it with attack patterns against multiple reasoning tasks simultaneously. Based on these, we conduct a study on how these attacks can be realized in physical traffic scenarios. Through our empirical study, we evaluate the effectiveness, transferability, and realizability of typographic attacks in traffic scenes. Our findings demonstrate particular harmfulness of the typographic attacks against existing Vision-LLMs (e.g., LLaVA, Qwen-VL, VILA, and Imp), thereby raising community awareness of vulnerabilities when incorporating such models into AD systems. We will release our source code upon acceptance.
Abstract:Deep learning-based lane detection (LD) plays a critical role in autonomous driving systems, such as adaptive cruise control. However, it is vulnerable to backdoor attacks. Existing backdoor attack methods on LD exhibit limited effectiveness in dynamic real-world scenarios, primarily because they fail to consider dynamic scene factors, including changes in driving perspectives (e.g., viewpoint transformations) and environmental conditions (e.g., weather or lighting changes). To tackle this issue, this paper introduces BadLANE, a dynamic scene adaptation backdoor attack for LD designed to withstand changes in real-world dynamic scene factors. To address the challenges posed by changing driving perspectives, we propose an amorphous trigger pattern composed of shapeless pixels. This trigger design allows the backdoor to be activated by various forms or shapes of mud spots or pollution on the road or lens, enabling adaptation to changes in vehicle observation viewpoints during driving. To mitigate the effects of environmental changes, we design a meta-learning framework to train meta-generators tailored to different environmental conditions. These generators produce meta-triggers that incorporate diverse environmental information, such as weather or lighting conditions, as the initialization of the trigger patterns for backdoor implantation, thus enabling adaptation to dynamic environments. Extensive experiments on various commonly used LD models in both digital and physical domains validate the effectiveness of our attacks, outperforming other baselines significantly (+25.15\% on average in Attack Success Rate). Our codes will be available upon paper publication.
Abstract:With the emergence of foundation models, deep learning-based object detectors have shown practical usability in closed set scenarios. However, for real-world tasks, object detectors often operate in open environments, where crucial factors (e.g., data distribution, objective) that influence model learning are often changing. The dynamic and intricate nature of the open environment poses novel and formidable challenges to object detectors. Unfortunately, current research on object detectors in open environments lacks a comprehensive analysis of their distinctive characteristics, challenges, and corresponding solutions, which hinders their secure deployment in critical real-world scenarios. This paper aims to bridge this gap by conducting a comprehensive review and analysis of object detectors in open environments. We initially identified limitations of key structural components within the existing detection pipeline and propose the open environment object detector challenge framework that includes four quadrants (i.e., out-of-domain, out-of-category, robust learning, and incremental learning) based on the dimensions of the data / target changes. For each quadrant of challenges in the proposed framework, we present a detailed description and systematic analysis of the overarching goals and core difficulties, systematically review the corresponding solutions, and benchmark their performance over multiple widely adopted datasets. In addition, we engage in a discussion of open problems and potential avenues for future research. This paper aims to provide a fresh, comprehensive, and systematic understanding of the challenges and solutions associated with open-environment object detectors, thus catalyzing the development of more solid applications in real-world scenarios. A project related to this survey can be found at https://github.com/LiangSiyuan21/OEOD_Survey.
Abstract:Large Language Models (LLMs), used in creative writing, code generation, and translation, generate text based on input sequences but are vulnerable to jailbreak attacks, where crafted prompts induce harmful outputs. Most jailbreak prompt methods use a combination of jailbreak templates followed by questions to ask to create jailbreak prompts. However, existing jailbreak prompt designs generally suffer from excessive semantic differences, resulting in an inability to resist defenses that use simple semantic metrics as thresholds. Jailbreak prompts are semantically more varied than the original questions used for queries. In this paper, we introduce a Semantic Mirror Jailbreak (SMJ) approach that bypasses LLMs by generating jailbreak prompts that are semantically similar to the original question. We model the search for jailbreak prompts that satisfy both semantic similarity and jailbreak validity as a multi-objective optimization problem and employ a standardized set of genetic algorithms for generating eligible prompts. Compared to the baseline AutoDAN-GA, SMJ achieves attack success rates (ASR) that are at most 35.4% higher without ONION defense and 85.2% higher with ONION defense. SMJ's better performance in all three semantic meaningfulness metrics of Jailbreak Prompt, Similarity, and Outlier, also means that SMJ is resistant to defenses that use those metrics as thresholds.
Abstract:Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. However, we uncover the potential threat posed by backdoor attacks on autoregressive VLMs during instruction tuning. Adversaries can implant a backdoor by injecting poisoned samples with triggers embedded in instructions or images, enabling malicious manipulation of the victim model's predictions with predefined triggers. Nevertheless, the frozen visual encoder in autoregressive VLMs imposes constraints on the learning of conventional image triggers. Additionally, adversaries may encounter restrictions in accessing the parameters and architectures of the victim model. To address these challenges, we propose a multimodal instruction backdoor attack, namely VL-Trojan. Our approach facilitates image trigger learning through an isolating and clustering strategy and enhance black-box-attack efficacy via an iterative character-level text trigger generation method. Our attack successfully induces target outputs during inference, significantly surpassing baselines (+62.52\%) in ASR. Moreover, it demonstrates robustness across various model scales and few-shot in-context reasoning scenarios.