相关论文: VL-Trojan: Multimodal Instruction Backdoor Attacks…

Deep learning has come a long way and has enjoyed an unprecedented success. Despite high accuracy, however, deep models are brittle and are easily fooled by imperceptible adversarial perturbations. In contrast to common inference-time…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

As audio-visual multi-modal large language models (MLLMs) are increasingly deployed in safety-critical applications, understanding their vulnerabilities is crucial. To this end, we introduce Multi-Modal Typography, a systematic study…

Deploying large vision-language models (LVLMs) introduces a unique vulnerability: susceptibility to malicious attacks via visual inputs. However, existing defense methods suffer from two key limitations: (1) They solely focus on textual…

A backdoor or Trojan attack is an important type of data poisoning attack against deep neural network (DNN) classifiers, wherein the training dataset is poisoned with a small number of samples that each possess the backdoor pattern (usually…

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial attacks generate…

Visual State Space Models (VSSM) have shown remarkable performance in various computer vision tasks. However, backdoor attacks pose significant security challenges, causing compromised models to predict target labels when specific triggers…

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Backdoor attacks creating 'sleeper agents' in large language models (LLMs) pose significant safety risks. This study employs mechanistic interpretability to explore resulting internal structural differences. Comparing clean Qwen2.5-3B…

Prompts have significantly improved the performance of pretrained Large Language Models (LLMs) on various downstream tasks recently, making them increasingly indispensable for a diverse range of LLM application scenarios. However, the…

Typical large vision-language models (LVLMs) apply autoregressive supervision solely to textual sequences, without fully incorporating the visual modality into the learning process. This results in three key limitations: (1) an inability to…

Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into…

The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates the novel challenge of defending MLLMs against such…

Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous driving and robotic manipulation. Recent research has…

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the…

While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…

Recent work has shown that the introduction of autonomous vehicles (AVs) in traffic could help reduce traffic jams. Deep reinforcement learning methods demonstrate good performance in complex control problems, including autonomous vehicle…

Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous research on interpretability for LLM safety tends to focus…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where a backdoored model behaves normally with clean inputs but exhibits attacker-specified behaviors upon the inputs containing triggers. Most previous backdoor attacks mainly…