Related papers: BadLLM-TG: A Backdoor Defender powered by LLM Trig…

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…

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

Inference optimization is a vital technique for deploying LLMs at scale. Compilation is the most widely adopted optimization technique for LLMs. While it assumes semantic equivalence between the original and compiled graphs, we first…

The advent of clinical language models integrated into electronic health records (EHR) for clinical decision support has marked a significant advancement, leveraging the depth of clinical notes for improved decision-making. Despite their…

Large Language Models (LLMs) have become integral to many applications, with system prompts serving as a key mechanism to regulate model behavior and ensure ethical outputs. In this paper, we introduce a novel backdoor attack that…

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

The emergence of graph foundation models (GFMs), particularly those incorporating language models (LMs), has revolutionized graph learning and demonstrated remarkable performance on text-attributed graphs (TAGs). However, compared to…

Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample-wise to more fine-grained sentence element-wise (e.g.,…

Large language models (LLMs) have exhibited outstanding performance in natural language processing tasks. However, these models remain susceptible to adversarial attacks in which slight input perturbations can lead to harmful or misleading…

With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…

Backdoor attack against deep neural networks is currently being profoundly investigated due to its severe security consequences. Current state-of-the-art backdoor attacks require the adversary to modify the input, usually by adding a…

The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…

Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token level and lack deeper semantic manipulation, which limits stealthiness. In addition, Prior…

Deep neural networks (DNNs) have long been recognized as vulnerable to backdoor attacks. By providing poisoned training data in the fine-tuning process, the attacker can implant a backdoor into the victim model. This enables input samples…

Large language models (LLMs) have exhibited remarkable versatility and adaptability, while their widespread adoption across various applications also raises critical safety concerns. This paper focuses on the impact of backdoored LLMs.…

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,…

Safety is a paramount concern for large language models (LLMs) in open deployment, motivating the development of safeguard methods that enforce ethical and responsible use through safety alignment or guardrail mechanisms. Jailbreak attacks…

Large Language Models (LLMs) are constrained by outdated information and a tendency to generate incorrect data, commonly referred to as "hallucinations." Retrieval-Augmented Generation (RAG) addresses these limitations by combining the…

Despite significant advancements, large language models (LLMs) still struggle with providing accurate answers when lacking domain-specific or up-to-date knowledge. Retrieval-Augmented Generation (RAG) addresses this limitation by…