Related papers: Detecting Stealthy Backdoor Samples based on Intra…

Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…

Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it…

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…

Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behavior undermines models' helpfulness and restricts usability…

Large Language Models (LLMs), despite their impressive capabilities across domains, have been shown to be vulnerable to backdoor attacks. Prior backdoor strategies predominantly operate at the token level, where an injected trigger causes…

Federated learning (FL) is vulnerable to backdoor attacks, where adversaries alter model behavior on target classification labels by embedding triggers into data samples. While these attacks have received considerable attention in…

As large language models (LLMs) are increasingly fine-tuned for hardware tasks like RTL code generation, the scarcity of high-quality datasets often leads to the use of rapidly assembled or generated training data. These datasets frequently…

Federated learning is a distributed framework designed to address privacy concerns. However, it introduces new attack surfaces, which are especially prone when data is non-Independently and Identically Distributed. Existing approaches fail…

In recent years, large language models (LLMs) have significantly advanced the field of natural language processing (NLP). By fine-tuning LLMs with data from specific scenarios, these foundation models can better adapt to various downstream…

Federated Transfer Learning (FTL) is the most general variation of Federated Learning. According to this distributed paradigm, a feature learning pre-step is commonly carried out by only one party, typically the server, on publicly shared…

Developers increasingly construct multimodal large language models (MLLMs) by assembling pretrained components,introducing supply-chain attack surfaces.Existing security research primarily focuses on poisoning backbones such as encoders or…

Verifying the credibility of Cyber Threat Intelligence (CTI) is essential for reliable cybersecurity defense. However, traditional approaches typically treat this task as a static classification problem, relying on handcrafted features or…

Federated learning allows multiple participants to collaboratively train a central model without sharing their private data. However, this distributed nature also exposes new attack surfaces. In particular, backdoor attacks allow attackers…

The proliferation of open-weight Large Language Models (LLMs) has democratized agentic AI, yet fine-tuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance. This creates a risk where third-party…

Federated Learning (FL) as a distributed learning paradigm that aggregates information from diverse clients to train a shared global model, has demonstrated great success. However, malicious clients can perform poisoning attacks and model…

Backdoor attacks present a significant threat to the robustness of Federated Learning (FL) due to their stealth and effectiveness. They maintain both the main task of the FL system and the backdoor task simultaneously, causing malicious…

Speaker verification has been widely and successfully adopted in many mission-critical areas for user identification. The training of speaker verification requires a large amount of data, therefore users usually need to adopt third-party…

As Large Language Models (LLMs) become increasingly integrated into software development workflows, they also become prime targets for adversarial attacks. Among these, backdoor attacks are a significant threat, allowing attackers to…

Backdoor Attacks have been a serious vulnerability against Large Language Models (LLMs). However, previous methods only reveal such risk in specific models, or present tasks transferability after attacking the pre-trained phase. So, how…

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…