Related papers: Adversarial Distilled Retrieval-Augmented Guarding…

Adversarial training significantly improves adversarial robustness, but superior performance is primarily attained with large models. This substantial performance gap for smaller models has spurred active research into adversarial…

Large language model (LLM) agents deployed for multi-step tasks frequently fail in predictable ways: attempting actions with unmet preconditions, issuing redundant commands, or mishandling environment constraints. While retrieval-augmented…

Deep learning models are vulnerable to adversarial examples, posing critical security challenges in real-world applications. While Adversarial Training (AT ) is a widely adopted defense mechanism to enhance robustness, it often incurs a…

Safety guard models that detect malicious queries aimed at large language models (LLMs) are essential for ensuring the secure and responsible deployment of LLMs in real-world applications. However, deploying existing safety guard models…

Developing agents for complex and underspecified tasks, where no clear objective exists, remains challenging but offers many opportunities. This is especially true in video games, where simulated players (bots) need to play realistically,…

Large pre-trained Vision-Language Models (VLMs) such as Contrastive Language-Image Pre-training (CLIP) have been shown to be susceptible to adversarial attacks, raising concerns about their deployment in safety-critical applications like…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user queries. These systems, however, remain…

Adversarial attacks pose a significant threat to the security and safety of deep neural networks being applied to modern applications. More specifically, in computer vision-based tasks, experts can use the knowledge of model architecture to…

Adversarial distillation (AD) is a knowledge distillation technique that facilitates the transfer of robustness from teacher deep neural network (DNN) models to lightweight target (student) DNN models, enabling the target models to perform…

In the realm of Adversarial Distillation (AD), strategic and precise knowledge transfer from an adversarially robust teacher model to a less robust student model is paramount. Our Dynamic Guidance Adversarial Distillation (DGAD) framework…

We introduce Adversarial Sparse Teacher (AST), a robust defense method against distillation-based model stealing attacks. Our approach trains a teacher model using adversarial examples to produce sparse logit responses and increase the…

Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially…

Knowledge distillation is normally used to compress a big network, or teacher, onto a smaller one, the student, by training it to match its outputs. Recently, some works have shown that robustness against adversarial attacks can also be…

Federated learning faces increasing threats from model poisoning attacks, which harms its application to improve privacy. Existing defense methods typically rely on fixed thresholds or perform clustering with a fixed number of clusters to…

As the scale and complexity of jailbreaking attacks on large language models (LLMs) continue to escalate, their efficiency and practical applicability are constrained, posing a profound challenge to LLM security. Jailbreaking techniques…

Vision-Language Models (VLMs) are increasingly deployed in safety-critical applications, making their adversarial robustness a crucial concern. While adversarial knowledge distillation has shown promise in transferring robustness from…

In this paper, we tackle the emerging challenge of unintended harmful content generation in Large Language Models (LLMs) with a novel dual-stage optimisation technique using adversarial fine-tuning. Our two-pronged approach employs an…

Adversarial Robustness Distillation (ARD) is a promising task to boost the robustness of small-capacity models with the guidance of the pre-trained robust teacher. The ARD can be summarized as a min-max optimization process, i.e.,…

Knowledge distillation (KD) has been shown to be highly effective in guiding a student model with a larger teacher model and achieving practical benefits in improving the computational and memory efficiency for large language models (LLMs).…

Model distillation has become essential for creating smaller, deployable language models that retain larger system capabilities. However, widespread deployment raises concerns about resilience to adversarial manipulation. This paper…