Related papers: SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthet…

Multimodal Large Reasoning Models (MLRMs) demonstrate impressive cross-modal reasoning but often amplify safety risks under adversarial or unsafe prompts, a phenomenon we call the \textit{Reasoning Tax}. Existing defenses mainly act at the…

Recent progress in Multimodal Large Language Models (MLLMs) has unlocked powerful cross-modal reasoning abilities, but also raised new safety concerns, particularly when faced with adversarial multimodal inputs. To improve the safety of…

Large language models (LLMs) are widely used in real-world applications, raising concerns about their safety and trustworthiness. While red-teaming with jailbreak prompts exposes the vulnerabilities of LLMs, current efforts focus primarily…

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

Large Language Models (LLMs) can significantly improve their reasoning capabilities by interacting with external tools, a paradigm known as Tool-Integrated Reasoning (TIR). However, extending TIR to multi-turn scenarios using Reinforcement…

Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications. However, existing safety alignment methods typically suffer from safety-performance trade-offs and the…

Large language models (LLMs) are shown to be vulnerable to jailbreaking attacks where adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detecting and filtering…

As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the…

Alignment in LLMs is more brittle than commonly assumed: misalignment can be triggered by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors…

Despite the strong performance of large language models (LLMs) across diverse tasks, their susceptibility to adversarial attacks and unsafe content generation remains a significant obstacle to deployment, particularly in high-stakes…

Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing…

Multi-turn jailbreaks capture the real threat model for safety-aligned chatbots, where single-turn attacks are merely a special case. Yet existing approaches break under exploration complexity and intent drift. We propose SEMA, a simple yet…

Large Language Models (LLMs) trained for average correctness often exhibit mode collapse, producing narrow decision behaviors on tasks where multiple responses may be reasonable. This limitation is particularly problematic in ordinal…

Multi-modal Large Language Models (MLLMs) are increasingly deployed in interactive applications. However, their safety vulnerabilities become pronounced in multi-turn multi-modal scenarios, where harmful intent can be gradually…

Large language models increasingly rely on either reinforcement learning or multi-agent prompting to improve reasoning, yet these two paradigms remain difficult to combine. Directly applying single-agent reinforcement learning to multi-turn…

Deploying LLMs in multi-turn dialogues facilitates jailbreak attacks that distribute harmful intent across seemingly benign turns. Recent training-based multi-turn jailbreak methods learn long-horizon attack strategies from interaction…

Large Language Models (LLMs) face persistent and evolving trustworthiness issues, motivating developers to seek automated and flexible repair methods that enable convenient deployment across diverse scenarios. Existing repair methods like…

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

Large Language Models (LLMs) hold immense potential to generate synthetic data of high quality and utility, which has numerous applications from downstream model training to practical data utilisation. However, contemporary models, despite…

Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a lightweight alternative to expensive retraining. However,…