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

Recent advances in Large Language Models (LLMs) - particularly model scaling and test-time techniques - have greatly enhanced the reasoning capabilities of language models at the expense of higher inference costs. To lower inference costs,…

In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful content. The mainstream paradigm for LLM safety alignment…

As multimodal reasoning improves the overall capabilities of Large Vision Language Models (LVLMs), recent studies have begun to explore safety-oriented reasoning, aiming to enhance safety awareness by analyzing potential safety risks during…

Large Language Models (LLMs) exhibit impressive performance across diverse domains but often suffer from overconfidence, limiting their reliability in critical applications. We propose SteerConf, a novel framework that systematically steers…

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)…

As LLMs are increasingly deployed in real-world applications, ensuring their ability to refuse malicious prompts, especially jailbreak attacks, is essential for safe and reliable use. Recently, activation steering has emerged as an…

The performance bottleneck of Automatic Speech Recognition (ASR) in stuttering speech scenarios has limited its applicability in domains such as speech rehabilitation. This paper proposed an LLM-driven ASR-SED multi-task learning framework…

With the widespread use of multi-modal Large Language models (MLLMs), safety issues have become a growing concern. Multi-turn dialogues, which are more common in everyday interactions, pose a greater risk than single prompts; however,…

Self-alignment is an effective way to reduce the cost of human annotation while ensuring promising model capability. However, most current methods complete the data collection and training steps in a single round, which may overlook the…

Malicious attackers can exploit large language models (LLMs) by engaging them in multi-turn dialogues to achieve harmful objectives, posing significant safety risks to society. To address this challenge, we propose a novel defense…

The SEAR Dataset is a novel multimodal resource designed to study the emerging threat of social engineering (SE) attacks orchestrated through augmented reality (AR) and multimodal large language models (LLMs). This dataset captures 180…

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal…

We introduce SteeringSafety, a systematic framework for evaluating representation steering methods across seven safety perspectives spanning 17 datasets. While prior work highlights general capabilities of representation steering, we…

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although multi-turn jailbreaks are empirically effective, the structure of conversational safety failure…

We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than…

Ensuring the safety of Large Language Models (LLMs) is critical for real-world deployment. However, current safety measures often fail to address implicit, domain-specific risks. To investigate this gap, we introduce a dataset of 3,000…

Multimodal Large Language Models (MLLMs) have made rapid progress in single-video understanding, yet their ability to reason across multiple independent video streams remains poorly understood. Existing multi-video benchmarks rely largely…

Multi-turn jailbreak attacks progressively erode LLM safety alignment across seemingly innocuous conversation turns, achieving success rates exceeding 90% against state-of-the-art models. Existing alignment-based and guardrail methods…

Current methods for content safety in Large Language Models (LLMs), such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), often rely on multi-stage training pipelines and lack fine-grained,…