相关论文: Jailbreaking as a Reward Misspecification Problem

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to…

While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs to exhibit…

Large Language Models (LLMs) remain vulnerable to jailbreak attacks, which attempt to elicit harmful responses from LLMs. The evolving nature and diversity of these attacks pose many challenges for defense systems, including (1) adaptation…

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…

Jailbreaking large language models (LLMs) has emerged as a pressing concern with the increasing prevalence and accessibility of conversational LLMs. Adversarial users often exploit these models through carefully engineered prompts to elicit…

The exploitation of large language models (LLMs) for malicious purposes poses significant security risks as these models become more powerful and widespread. While most existing red-teaming frameworks focus on single-turn attacks,…

Large Language Model (LLM) safeguards, which implement request refusals, have become a widely adopted mitigation strategy against misuse. At the intersection of adversarial machine learning and AI safety, safeguard red teaming has…

Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulnerability in which the previous response in the dialogue can…

Numerous studies have investigated methods for jailbreaking Large Language Models (LLMs) to generate harmful content. Typically, these methods are evaluated using datasets of malicious prompts designed to bypass security policies…

Large Multimodal Models (LMMs) have demonstrated the ability to interact with humans under real-world conditions by combining Large Language Models (LLMs) and modality encoders to align multimodal information (visual and auditory) with…

A key challenge in reinforcement learning (RL) is reward (mis)specification, whereby imprecisely defined reward functions can result in unintended, possibly harmful, behaviours. Indeed, reward functions in RL are typically treated as…

Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while…

Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbreak attacks have been proposed to bypass the safety…

Multimodal large language models (MLLMs) are widely used in vision-language reasoning tasks. However, their vulnerability to adversarial prompts remains a serious concern, as safety mechanisms often fail to prevent the generation of harmful…

Reinforcement learning (RL) trained language model agents with tool access are increasingly deployed in coding assistants, research tools, and autonomous systems. We introduce the Reward Hacking Benchmark (RHB), a suite of multi-step tasks…

Automated red-teaming has become a crucial approach for uncovering vulnerabilities in large language models (LLMs). However, most existing methods focus on isolated safety flaws, limiting their ability to adapt to dynamic defenses and…

Reward models are central to aligning large language models, yet they often overfit to spurious cues such as response length and overly agreeable tone. Most prior work weakens these cues directly by penalizing or controlling specific…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety…