Related papers: Relationship-Aware Safety Unlearning for Multimoda…

Although Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, growing concerns have emerged over the misuse of sensitive, copyrighted, or harmful data during training. To address these…

The impressive capability of modern text-to-image models to generate realistic visuals has come with a serious drawback: they can be misused to create harmful, deceptive or unlawful content. This has accelerated the push for machine…

Vision Language Action (VLA) models close the perception action loop by translating multimodal instructions into executable behaviors, but this very capability magnifies safety risks: jailbreaks that merely yield toxic text in LLMs can…

There have been a couple of studies showing that attempting to erase multilingual knowledge using only English data is insufficient for multilingual LLMs. However, their analyses remain highly performance-oriented. In this paper, we switch…

Large language models (LLMs) trained over extensive corpora risk memorizing sensitive, copyrighted, or toxic content. To address this, we propose \textbf{OBLIVIATE}, a robust unlearning framework that removes targeted data while preserving…

Multimodal Large Language Models (MLLMs) are susceptible to the implicit reasoning risk, wherein innocuous unimodal inputs synergistically assemble into risky multimodal data that produce harmful outputs. We attribute this vulnerability to…

Large Multimodal Reasoning Models (LMRMs) are moving into real applications, where they must be both useful and safe. Safety is especially challenging in multimodal settings: images and text can be combined to bypass guardrails, and single…

The security of biomedical Multimodal Large Language Models (MLLMs) has attracted increasing attention. However, training samples easily contain private information and incorrect knowledge that are difficult to detect, potentially leading…

Lifelong multimodal agents must continuously adapt to new tasks through post-training, but this creates a fundamental tension between acquiring capabilities and preserving safety alignment. We demonstrate that fine-tuning aligned…

Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attacks. Existing defenses predominantly rely on safety…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Large Vision-Language Models face growing safety challenges with multimodal inputs. This paper introduces the concept of Implicit Reasoning Safety, a vulnerability in LVLMs. Benign combined inputs trigger unsafe LVLM outputs due to flawed…

This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse…

Multimodal Language Models (MMLMs) typically undergo post-training alignment to prevent harmful content generation. However, these alignment stages focus primarily on the assistant role, leaving the user role unaligned, and stick to a fixed…

As Multimodal Large Language Models (MLLMs) acquire stronger reasoning capabilities to handle complex, multi-image instructions, this advancement may pose new safety risks. We study this problem by introducing MIR-SafetyBench, the first…

The need for machine unlearning is critical for data privacy, yet existing methods often cause Knowledge Contamination by unintentionally damaging related knowledge. Such a degraded model performance after unlearning has been recently…

Large-scale vision-and-language models, such as CLIP, are typically trained on web-scale data, which can introduce inappropriate content and lead to the development of unsafe and biased behavior. This, in turn, hampers their applicability…

Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety. Existing machine unlearning methods…

LLM have achieved success in many fields but still troubled by problematic content in the training corpora. LLM unlearning aims at reducing their influence and avoid undesirable behaviours. However, existing unlearning methods remain…

Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazardous capabilities from models and make them inaccessible to…