相关论文: Robust LLM safeguarding via refusal feature advers…

Reinforcement learning (RL) has achieved remarkable success in fields like robotics and autonomous driving, but adversarial attacks designed to mislead RL systems remain challenging. Existing approaches often rely on modifying the…

With the widespread use of machine learning, concerns over its security and reliability have become prevalent. As such, many have developed defenses to harden neural networks against adversarial examples, imperceptibly perturbed inputs that…

The rapid growth in both the scale and complexity of Android malware has driven the widespread adoption of machine learning (ML) techniques for scalable and accurate malware detection. Despite their effectiveness, these models remain…

Large Language Models (LLMs) are becoming a prominent generative AI tool, where the user enters a query and the LLM generates an answer. To reduce harm and misuse, efforts have been made to align these LLMs to human values using advanced…

Recently researchers have studied input leakage problems in Federated Learning (FL) where a malicious party can reconstruct sensitive training inputs provided by users from shared gradient. It raises concerns about FL since input leakage…

Despite recent efforts in Large Language Model (LLM) safety and alignment, current adversarial attacks on frontier LLMs can still consistently force harmful generations. Although adversarial training has been widely studied and shown to…

While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus…

Addressing the critical need for robust safety in Large Language Models (LLMs), particularly against adversarial attacks and in-distribution errors, we introduce Reinforcement Learning with Backtracking Feedback (RLBF). This framework…

Large Language Models (LLMs) are powerful tools with profound societal impacts, yet their ability to generate responses to diverse and uncontrolled inputs leaves them vulnerable to adversarial attacks. While existing defenses often struggle…

Safety alignment in large language models (LLMs), particularly for cybersecurity tasks, primarily focuses on preventing misuse. While this approach reduces direct harm, it obscures a complementary failure mode: denial of assistance to…

Federated learning has a variety of applications in multiple domains by utilizing private training data stored on different devices. However, the aggregation process in federated learning is highly vulnerable to adversarial attacks so that…

Safely aligning large language models (LLMs) often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods frequently rely on…

Adversarial attacks on Face Recognition (FR) systems have demonstrated significant effectiveness against standalone FR models. However, their practicality diminishes in complete FR systems that incorporate Face Anti-Spoofing (FAS) models,…

The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into…

Deep neural networks are susceptible to adversarial attacks, which can compromise their performance and accuracy. Adversarial Training (AT) has emerged as a popular approach for protecting neural networks against such attacks. However, a…

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…

Large language models (LLMs) achieve impressive performance across diverse tasks yet remain vulnerable to jailbreak attacks that bypass safety mechanisms. We present RAID (Refusal-Aware and Integrated Decoding), a framework that…

LLM have achieved success in many fields but still troubled by problematic content in the training corpora. LLM unlearning aims at reducing their influence and avoid undesirable behaviours. However, existing unlearning methods remain…

Given the widespread use of deep learning models in safety-critical applications, ensuring that the decisions of such models are robust against adversarial exploitation is of fundamental importance. In this thesis, we discuss recent…

The capabilities of large language models (LLMs) are widely regarded as relying on autoregressive models (ARMs). We challenge this notion by introducing LLaDA, a diffusion model trained from scratch under the pre-training and supervised…