Related papers: Robust Anti-Backdoor Instruction Tuning in LVLMs

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-following abilities and inability to distinguish the…

Instruction tuning -- supervised fine-tuning using instruction-response pairs -- is a key step in making pre-trained large language models (LLMs) instructable. Meanwhile, LLMs perform multitask learning during their pre-training, acquiring…

Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision-language models (VLMs). While RL-tuned VLMs improve on visual…

Backdoor attacks are a significant threat to the performance and integrity of pre-trained language models. Although such models are routinely fine-tuned for downstream NLP tasks, recent work shows they remain vulnerable to backdoor attacks…

Reinforcement Learning with Verifiable Rewards (RLVR) is an emerging paradigm that significantly boosts a Large Language Model's (LLM's) reasoning abilities on complex logical tasks, such as mathematics and programming. However, we…

Multimodal contrastive learning models (e.g., CLIP) can learn high-quality representations from large-scale image-text datasets, while they exhibit significant vulnerabilities to backdoor attacks, raising serious safety concerns. In this…

Visual language models (VLMs) have made significant progress in image captioning tasks, yet recent studies have found they are vulnerable to backdoor attacks. Attackers can inject undetectable perturbations into the data during inference,…

The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that…

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…

Multimodal large language models have become an important infrastructure for unified processing of visual and linguistic tasks. However, such models are highly susceptible to backdoor implantation during supervised fine-tuning and will…

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the-art natural…

Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studied in unimodal…

Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often compromises their previously established safety alignment. To mitigate the degradation of model safety during fine-tuning, we introduce LookAhead…

Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, we propose…

The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studies have demonstrated the feasibility of backdoor attacks against LLMs. However, existing…

As Large Language Models (LLMs) gain traction across critical domains, ensuring secure and trustworthy training processes has become a major concern. Backdoor attacks, where malicious actors inject hidden triggers into training data, are…

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…