Related papers: Model-Agnostic Lifelong LLM Safety via Externalize…

The vulnerability of Vision Large Language Models (VLLMs) to jailbreak attacks appears as no surprise. However, recent defense mechanisms against these attacks have reached near-saturation performance on benchmark evaluations, often with…

Safety alignment is critical in pre-training large language models (LLMs) to generate responses aligned with human values and refuse harmful queries. Unlike LLM, the current safety alignment of VLMs is often achieved with post-hoc safety…

The emergence of Large Reasoning Models (LRMs) introduces a new paradigm of explicit reasoning, enabling remarkable advances yet posing unique risks such as reasoning manipulation and information leakage. To mitigate these risks, current…

Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rather than elicited by…

Large Language Models (LLMs) serve as the backbone of modern AI systems, yet they remain susceptible to adversarial jailbreak attacks. Consequently, robust detection of such malicious inputs is paramount for ensuring model safety.…

Large Language Models (LLMs) are widely applied in decision making, but their deployment is threatened by jailbreak attacks, where adversarial users manipulate model behavior to bypass safety measures. Existing defense mechanisms, such as…

Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or automatic methods, which have their own limitations on…

The proliferation of jailbreak attacks against large language models (LLMs) highlights the need for robust security measures. However, in multi-round dialogues, malicious intentions may be hidden in interactions, leading LLMs to be more…

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, however, introduces fundamentally new reliability challenges…

While safety-aligned large language models (LLMs) are increasingly used as the cornerstone for powerful systems such as multi-agent frameworks to solve complex real-world problems, they still suffer from potential adversarial queries, such…

With the growing deployment of large language models (LLMs) in real-world applications, establishing robust safety guardrails to moderate their inputs and outputs has become essential to ensure adherence to safety policies. Current…

Deep Neural Networks remain inherently vulnerable to backdoor attacks. Traditional test-time defenses largely operate under the paradigm of internal diagnosis methods like model repairing or input robustness, yet these approaches are often…

The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to…

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…

The widespread adoption of Large Language Models (LLMs), exemplified by OpenAI's ChatGPT, brings to the forefront the imperative to defend against adversarial threats on these models. These attacks, which manipulate an LLM's output by…

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Large language models (LLMs) have achieved record adoption in a short period of time across many different sectors including high importance areas such as education [4] and healthcare [23]. LLMs are open-ended models trained on diverse data…

Adapting large language models (LLMs) to a targeted task efficiently and effectively remains a fundamental challenge. Such adaptation often requires iteratively improving the model toward a targeted task, yet collecting high-quality…