相关论文: TrojFM: Resource-efficient Backdoor Attacks agains…

Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly…

Federated Learning (FL) is a popular distributed machine learning paradigm that enables jointly training a global model without sharing clients' data. However, its repetitive server-client communication gives room for backdoor attacks with…

In a backdoor attack on a machine learning model, an adversary produces a model that performs well on normal inputs but outputs targeted misclassifications on inputs containing a small trigger pattern. Model compression is a widely-used…

The emergence of graph foundation models (GFMs), particularly those incorporating language models (LMs), has revolutionized graph learning and demonstrated remarkable performance on text-attributed graphs (TAGs). However, compared to…

Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new vulnerability surface. We present the Deadlock Attack, a…

Recent advancements have led to the widespread adoption of code-oriented large language models (Code LLMs) for programming tasks. Despite their success in deployment, their security research is left far behind. This paper introduces a new…

Large Language Models (LLMs) have become integral to many applications, with system prompts serving as a key mechanism to regulate model behavior and ensure ethical outputs. In this paper, we introduce a novel backdoor attack that…

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…

Federated Learning (FL) enables numerous participants to train deep learning models collaboratively without exposing their personal, potentially sensitive data, making it a promising solution for data privacy in collaborative training. The…

Outsourced deep neural networks have been demonstrated to suffer from patch-based trojan attacks, in which an adversary poisons the training sets to inject a backdoor in the obtained model so that regular inputs can be still labeled…

The integration of large language models (LLMs) into robotic control pipelines enables natural language interfaces that translate user prompts into executable commands. However, this digital-to-physical interface introduces a critical and…

Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific…

Deep learning models are increasingly used in mobile applications as critical components. Unlike the program bytecode whose vulnerabilities and threats have been widely-discussed, whether and how the deep learning models deployed in the…

Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled conditions. However, most backdoor attacks have to modify the…

Model quantization is a popular technique for deploying deep learning models on resource-constrained environments. However, it may also introduce previously overlooked security risks. In this work, we present QuRA, a novel backdoor attack…

Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production deployments. We present Prompt Fencing, a novel architectural approach that applies cryptographic…

Research on backdoor attacks in Federated Learning (FL) has accelerated in recent years, with new attacks and defenses continually proposed in an escalating arms race. However, the evaluation of these methods remains neither standardized…

While Large Language Models (LLMs) have achieved remarkable progress, they remain vulnerable to jailbreak attacks. Existing methods, primarily relying on discrete input optimization (e.g., GCG), often suffer from high computational costs…

With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…

In this fast-evolving area of LLMs, our paper discusses the significant security risk presented by prompt injection attacks. It focuses on small open-sourced models, specifically the LLaMA family of models. We introduce novel defense…