Related papers: Transferring Backdoors between Large Language Mode…
Large language models (LLMs) have exhibited remarkable versatility and adaptability, while their widespread adoption across various applications also raises critical safety concerns. This paper focuses on the impact of backdoored LLMs.…
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attacks have surged, yet training effective on-device detectors requires labelled threat data that quickly becomes outdated.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…
With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing…
Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…
Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abilities while being…
We investigate whether knowledge distillation (KD) from multiple heterogeneous teacher models can enhance the generation of transferable adversarial examples. A lightweight student model is trained using two KD strategies: curriculum-based…
Generative large language models are crucial in natural language processing, but they are vulnerable to backdoor attacks, where subtle triggers compromise their behavior. Although backdoor attacks against LLMs are constantly emerging,…
Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…
Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…
The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…
Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to backdoor attacks, where…
Traditional distributed backdoor attacks (DBA) in federated learning improve stealthiness by decomposing global triggers into sub-triggers, which however requires more poisoned data to maintian the attck strength and hence increases the…
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…
The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…
Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by…
Pre-trained Natural Language Processing (NLP) models can be easily adapted to a variety of downstream language tasks. This significantly accelerates the development of language models. However, NLP models have been shown to be vulnerable to…
Dataset distillation offers a potential means to enhance data efficiency in deep learning. Recent studies have shown its ability to counteract backdoor risks present in original training samples. In this study, we delve into the theoretical…
Pre-trained language models have been applied to various NLP tasks with considerable performance gains. However, the large model sizes, together with the long inference time, limit the deployment of such models in real-time applications.…
Deep neural networks (DNNs) have long been recognized as vulnerable to backdoor attacks. By providing poisoned training data in the fine-tuning process, the attacker can implant a backdoor into the victim model. This enables input samples…
Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…