相关论文: EVA: Editing for Versatile Alignment against Jailb…

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs). A considerable amount of research exists proposing more effective jailbreak attacks, including the…

Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerability during this process, where malicious samples can…

Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…

Large vision-language models (VLMs) are highly vulnerable to multimodal jailbreak attacks that exploit visual-textual interactions to bypass safety guardrails. In this paper, we present DTR, a novel inference-time defense that mitigates…

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Guardrails are critical for the safe deployment of Large Language Models (LLMs)-powered software. Unlike traditional rule-based systems with limited, predefined input-output spaces that inherently constrain unsafe behavior, LLMs enable…

Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness…

We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…

Recent advances in large vision-language models (VLMs) have demonstrated remarkable success across a wide range of visual understanding tasks. However, the robustness of these models against jailbreak attacks remains an open challenge. In…

Recently, Automated Vulnerability Localization (AVL) has attracted growing attention, aiming to facilitate diagnosis by pinpointing the specific lines of code responsible for vulnerabilities. Large Language Models (LLMs) have shown…

This paper investigates the impact of model compression on the way Large Language Models (LLMs) process prompts, particularly concerning jailbreak resistance. We show that moderate WANDA pruning can enhance resistance to jailbreaking…

Vision-Language Models (VLMs) have gained considerable prominence in recent years due to their remarkable capability to effectively integrate and process both textual and visual information. This integration has significantly enhanced…

Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…

Research endeavors have been made in learning robust Multimodal Large Language Models (MLLMs) against jailbreak attacks. However, existing methods for improving MLLMs' robustness still face critical challenges: \ding{172} how to efficiently…

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Recent studies reveal that vision-language models (VLMs) become more susceptible to harmful requests and jailbreak attacks after integrating the vision modality, exhibiting greater vulnerability than their text-only LLM backbones. To…

Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images. However, their susceptibility to generating harmful content when exposed to unsafe queries raises…

Metaphor serves as an implicit approach to convey information, while enabling the generalized comprehension of complex subjects. However, metaphor can potentially be exploited to bypass the safety alignment mechanisms of Large Language…

Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…

Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…