相关论文: Adversarial Distilled Retrieval-Augmented Guarding…

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to mitigate LLM hallucinations and enhance their performance in knowledge-intensive domains. However, these systems are vulnerable to adversarial poisoning…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attack surfaces within…

Retrieval-Augmented Generation (RAG) is widely used to augment large language models with external knowledge retrieval to improve reliability and generalization. However, recent studies have shown that RAG systems remain vulnerable to data…

With the emergence of large language models, such as LLaMA and OpenAI GPT-3, In-Context Learning (ICL) gained significant attention due to its effectiveness and efficiency. However, ICL is very sensitive to the choice, order, and verbaliser…

Large Language Models (LLMs) are increasingly exposed to adaptive jailbreaking, particularly in high-stakes Chemical, Biological, Radiological, and Nuclear (CBRN) domains. Although streaming probes enable real-time monitoring, they still…

Adversarial training is the most promising method for learning robust models against adversarial examples. A recent study has shown that knowledge distillation between the same architectures is effective in improving the performance of…

The deployment and application of Large Language Models (LLMs) is hindered by their memory inefficiency, computational demands, and the high costs of API inferences. Traditional distillation methods, which transfer the capabilities of LLMs…

Large Language Models (LLMs) remain vulnerable to jailbreak attacks, which attempt to elicit harmful responses from LLMs. The evolving nature and diversity of these attacks pose many challenges for defense systems, including (1) adaptation…

Adversarial training is one effective approach for training robust deep neural networks against adversarial attacks. While being able to bring reliable robustness, adversarial training (AT) methods in general favor high capacity models,…

Large language models (LLMs) have transformed natural language processing (NLP), enabling applications from content generation to decision support. Retrieval-Augmented Generation (RAG) improves LLMs by incorporating external knowledge but…

Adversarial training is a widely adopted strategy to bolster the robustness of neural network models against adversarial attacks. This paper revisits the fundamental assumptions underlying image classification and suggests that representing…

Adversarial robustness distillation (ARD) aims to transfer both performance and robustness from teacher model to lightweight student model, enabling resilient performance on resource-constrained scenarios. Though existing ARD approaches…

SMS-based phishing (smishing) attacks have surged, yet training effective on-device detectors requires labelled threat data that quickly becomes outdated. To deal with this issue, we present Agentic Knowledge Distillation, which consists of…

Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss shows that the accumulated errors of easily-classified samples…

Knowledge distillation is effective for producing small, high-performance neural networks for classification, but these small networks are vulnerable to adversarial attacks. This paper studies how adversarial robustness transfers from…

Large Language Models (LLMs) are constrained by outdated information and a tendency to generate incorrect data, commonly referred to as "hallucinations." Retrieval-Augmented Generation (RAG) addresses these limitations by combining the…

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Federated learning is highly susceptible to model poisoning attacks, especially those meticulously crafted for servers. Traditional defense methods mainly focus on updating assessments or robust aggregation against manually crafted myopic…

Adversarial Training is a practical approach for improving the robustness of deep neural networks against adversarial attacks. Although bringing reliable robustness, the performance towards clean examples is negatively affected after…

Large language models (LLMs) are proven to benefit a lot from retrieval-augmented generation (RAG) in alleviating hallucinations confronted with knowledge-intensive questions. RAG adopts information retrieval techniques to inject external…