Related papers: AutoBackdoor: Automating Backdoor Attacks via LLM …

Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…

Backdoors implanted in pre-trained language models (PLMs) can be transferred to various downstream tasks, which exposes a severe security threat. However, most existing backdoor attacks against PLMs are un-targeted and task-specific. Few…

Early research into data poisoning attacks against Large Language Models (LLMs) demonstrated the ease with which backdoors could be injected. More recent LLMs add step-by-step reasoning, expanding the attack surface to include the…

Recently, Large Language Model (LLM)-empowered recommender systems (RecSys) have brought significant advances in personalized user experience and have attracted considerable attention. Despite the impressive progress, the research question…

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

Deep speech classification tasks, including keyword spotting and speaker verification, are vital in speech-based human-computer interaction. Recently, the security of these technologies has been revealed to be susceptible to backdoor…

Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this…

Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This…

Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics. However, their complex multimodal interactions also expose new security vulnerabilities. In this paper, we investigate a…

The rapid deployment of large language model (LLM)-based agents in real-world applications has raised serious concerns about their trustworthiness. In this work, we reveal the security and robustness vulnerabilities of these agents through…

As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on vulnerabilities in single-agent LLMs. These include prompt…

Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled conditions. However, most backdoor attacks have to modify the…

Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concentrated on aligning LLMs with human preferences and…

Recently, web-based Large Language Model (LLM) agents autonomously perform increasingly complex tasks, thereby bringing significant convenience. However, they also amplify the risks of malicious misuse cases such as unauthorized collection…

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…

Recent research has confirmed the feasibility of backdoor attacks in deep reinforcement learning (RL) systems. However, the existing attacks require the ability to arbitrarily modify an agent's observation, constraining the application…

Large reasoning models (LRMs) have emerged as a significant advancement in artificial intelligence, representing a specialized class of large language models (LLMs) designed to tackle complex reasoning tasks. The defining characteristic of…

With the growing adoption of reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs), the risk of backdoor installation during alignment has increased, leading to unintended and harmful behaviors.…

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…

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by…