相关论文: JAB: Joint Adversarial Prompting and Belief Augmen…

Multi-Agent Debate (MAD), leveraging collaborative interactions among Large Language Models (LLMs), aim to enhance reasoning capabilities in complex tasks. However, the security implications of their iterative dialogues and role-playing…

Retrieval-augmented generation (RAG) has emerged as a popular solution to mitigate the hallucination issues of large language models. However, existing studies on RAG seldom address the issue of predictive uncertainty, i.e., how likely it…

While deep learning has led to remarkable results on a number of challenging problems, researchers have discovered a vulnerability of neural networks in adversarial settings, where small but carefully chosen perturbations to the input can…

Adversarial ranking attacks have gained increasing attention due to their success in probing vulnerabilities, and, hence, enhancing the robustness, of neural ranking models. Conventional attack methods employ perturbations at a single…

While large language models (LLMs) exhibit remarkable capabilities across various tasks, they encounter potential security risks such as jailbreak attacks, which exploit vulnerabilities to bypass security measures and generate harmful…

For black-box attacks, the gap between the substitute model and the victim model is usually large, which manifests as a weak attack performance. Motivated by the observation that the transferability of adversarial examples can be improved…

This work concerns the development of deep networks that are certifiably robust to adversarial attacks. Joint robust classification-detection was recently introduced as a certified defense mechanism, where adversarial examples are either…

Large Language Models (LLMs) can justify or critique their predictions through discussions with other models or humans, thereby enriching their intrinsic understanding of instances. While proactive discussions in the inference phase have…

The application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adversarial perturbations can fool deep neural networks into…

Retrieval-Augmented Generation (RAG) is applied to solve hallucination problems and real-time constraints of large language models, but it also induces vulnerabilities against retrieval corruption attacks. Existing research mainly explores…

While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…

The emergence of Large Language Models (LLMs) has revealed a growing need for human-AI collaboration, especially in creative decision-making scenarios where trust and reliance are paramount. Through human studies and model evaluations on…

Despite rapid advancements in text-to-image (T2I) models, their safety mechanisms are vulnerable to adversarial prompts, which maliciously generate unsafe images. Current red-teaming methods for proactively assessing such vulnerabilities…

Harmful text detection has become a crucial task in the development and deployment of large language models, especially as AI-generated content continues to expand across digital platforms. This study proposes a joint retrieval framework…

Reward modeling has emerged as a promising approach for the scalable alignment of language models. However, contemporary reward models (RMs) often lack robustness, awarding high rewards to low-quality, out-of-distribution (OOD) samples.…

Large Language Model (LLM)-based Multi-Agent Systems (MASs) are increasingly deployed for agentic tasks, such as web automation, itinerary planning, and collaborative problem solving. Yet, their interactive nature introduces new security…

In realistic environments, speech is usually interfered by various noise and reverberation, which dramatically degrades the performance of automatic speech recognition (ASR) systems. To alleviate this issue, the commonest way is to use a…

Recent research has proved that deep neural networks (DNNs) are vulnerable to adversarial examples, the legitimate input added with imperceptible and well-designed perturbations can fool DNNs easily in the testing stage. However, most of…

Black-box adversarial attacks have demonstrated strong potential to compromise machine learning models by iteratively querying the target model or leveraging transferability from a local surrogate model. Recently, such attacks can be…

In Large Language Models, Retrieval-Augmented Generation (RAG) systems can significantly enhance the performance of large language models by integrating external knowledge. However, RAG also introduces new security risks. Existing research…