Related papers: Securing Multi-turn Conversational Language Models…

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…

Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abilities while being…

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks. However, they remain vulnerable to backdoor attacks, where models behave normally for…

Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive (AR) language models, enabling parallel generation and bidirectional context modeling. Yet their security implications,…

Multi-turn interaction in the dialogue system research refers to a system's ability to maintain context across multiple dialogue turns, enabling it to generate coherent and contextually relevant responses. Recent advancements in large…

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:…

Large language models (LLMs), known for their capability in understanding and following instructions, are vulnerable to adversarial attacks. Researchers have found that current commercial LLMs either fail to be "harmless" by presenting…

Large Audio Language Models (LALMs) have significantly advanced audio understanding but introduce critical security risks, particularly through audio jailbreaks. While prior work has focused on English-centric attacks, we expose a far more…

The rise of Large Language Models (LLMs) has revolutionized our comprehension of intelligence bringing us closer to Artificial Intelligence. Since their introduction, researchers have actively explored the applications of LLMs across…

Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs. These solutions facilitate tailored LLM creation via natural language prompts without coding. However, the trustworthiness…

Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised…

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

Code LLMs are increasingly employed in software development. However, studies have shown that they are vulnerable to backdoor attacks: when a trigger (a specific input pattern) appears in the input, the backdoor will be activated and cause…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a consequence, any input that contains the trigger will cause the…

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to…

Backdoor attacks on language models pose a growing security concern, yet the internal mechanisms by which a trigger sequence hijacks model computations remain poorly understood. We identify a circuit underlying a language-switching backdoor…