相关论文: Audio Jailbreak: An Open Comprehensive Benchmark f…
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…
Current jailbreaking work on large language models (LLMs) aims to elicit unsafe outputs from given prompts. However, it only focuses on single-turn jailbreaking targeting one specific query. On the contrary, the advanced LLMs are designed…
Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety…
Multimodal large language models (MLLMs) have achieved remarkable progress, yet remain critically vulnerable to adversarial attacks that exploit weaknesses in cross-modal processing. We present a systematic study of multimodal jailbreaks…
As large language models (LLMs) become increasingly deployed, understanding the complexity and evolution of jailbreaking strategies is critical for AI safety. We present a mass-scale empirical analysis of jailbreak complexity across over 2…
Despite the implementation of safety alignment strategies, large language models (LLMs) remain vulnerable to jailbreak attacks, which undermine these safety guardrails and pose significant security threats. Some defenses have been proposed…
Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…
Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer.…
Recent advances in large language models (LLMs) have demonstrated remarkable potential in the field of natural language processing. Unfortunately, LLMs face significant security and ethical risks. Although techniques such as safety…
Conversational large language models are trained to refuse to answer harmful questions. However, emergent jailbreaking techniques can still elicit unsafe outputs, presenting an ongoing challenge for model alignment. To better understand how…
Large Audio Language Models (LALMs) are increasingly capable of reasoning over audio. However, existing benchmarks provide limited coverage of reasoning in polyphonic audio, where multiple sound events co-occur and induce compositional…
Multi-Agent Debate (MAD), leveraging collaborative interactions among Large Language Models (LLMs), aim to enhance reasoning capabilities in complex tasks. However, the security implications of their iterative dialogues and role-playing…
Safety alignment in large language models (LLMs) is increasingly compromised by jailbreak attacks, which can manipulate these models to generate harmful or unintended content. Investigating these attacks is crucial for uncovering model…
Recently, instruction-following audio-language models have received broad attention for human-audio interaction. However, the absence of benchmarks capable of evaluating audio-centric interaction capabilities has impeded advancements in…
Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…
Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based…
Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…
Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly vulnerable to jailbreak attacks that bypass safety alignment and induce harmful behaviors.…
Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment. Prior work shows that translating malicious prompts into other languages can…
Jailbreak attacks expose a persistent gap between the intended safety behavior of aligned large language models and their behavior under adversarial prompting. Existing automated methods are increasingly effective but each commits to a…