相关论文: Constitutional Classifiers++: Efficient Production…

In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…

Large Language Models (LLMs) have achieved remarkable success but remain highly susceptible to jailbreak attacks, in which adversarial prompts coerce models into generating harmful, unethical, or policy-violating outputs. Such attacks pose…

Large Language Models (LLMs) are increasingly deployed for task automation and content generation, yet their safety mechanisms remain vulnerable to circumvention through different jailbreaking techniques. In this paper, we introduce…

Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols. We introduce JAILBREAK…

As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…

We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks. Unlike prior defenses that operate primarily at the output level,…

We study the problem of efficiently producing, in an online fashion, generative models of scalar, multiclass, and vector-valued outcomes that cannot be falsified on the basis of the observed data and a pre-specified collection of…

Uncovering the mechanisms behind "jailbreaks" in large language models (LLMs) is crucial for enhancing their safety and reliability, yet these mechanisms remain poorly understood. Existing studies predominantly analyze jailbreak prompts by…

Large language models (LLMs), known for their capability in understanding and following instructions, are vulnerable to adversarial attacks. Researchers have found that current commercial LLMs either fail to be "harmless" by presenting…

Augmenting language models with image inputs may enable more effective jailbreak attacks through continuous optimization, unlike text inputs that require discrete optimization. However, new multimodal fusion models tokenize all input…

Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for detecting jailbreak prompts are primarily online moderation APIs or finetuned LLMs. These strategies, however, often require extensive and…

Jailbreak attacks bypass the guardrails of large language models to produce harmful outputs. In this paper, we ask whether the model outputs produced by existing jailbreaks are actually useful. For example, when jailbreaking a model to give…

Jailbreaking attacks on the vision modality typically rely on imperceptible adversarial perturbations, whereas attacks on the textual modality are generally assumed to require visible modifications (e.g., non-semantic suffixes). In this…

Large language models (LLMs) have seen rapid development in recent years, revolutionizing various applications and significantly enhancing convenience and productivity. However, alongside their impressive capabilities, ethical concerns and…

Jailbreak attacks on multimodal AI systems remain underexplored, even though unsafe image generation can have more severe consequences than unsafe text and current defenses are relatively immature. We introduce PAST2HARM, a simple yet…

Making classifiers robust to adversarial examples is hard. Thus, many defenses tackle the seemingly easier task of detecting perturbed inputs. We show a barrier towards this goal. We prove a general hardness reduction between detection and…

Large Language Models (LLMs) have achieved remarkable success in various domains but remain vulnerable to adversarial jailbreak attacks. Existing prompt-defense strategies, including parameter-modifying and parameter-free approaches, face…

Jailbreak attacks represent one of the most sophisticated threats to the security of large language models (LLMs). To deal with such risks, we introduce an innovative framework that can help evaluate the effectiveness of jailbreak attacks…

Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…

Deep neural classifiers have recently found tremendous success in data-driven control systems. However, existing models suffer from a trade-off between accuracy and adversarial robustness. This limitation must be overcome in the control of…