Related papers: MirageBackdoor: A Stealthy Attack that Induces Thi…

Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering…

Recent studies have discovered that Chain-of-Thought prompting (CoT) can dramatically improve the performance of Large Language Models (LLMs), particularly when dealing with complex tasks involving mathematics or reasoning. Despite the…

Large reasoning models (LRMs) extend large language models with explicit multi-step reasoning traces, but this capability introduces a new class of prompt-induced inference-time denial-of-service (PI-DoS) attacks that exploit the high…

Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a consequence, any input that contains the trigger will cause the…

Neural code models (NCMs) have been widely used to address various code understanding tasks, such as defect detection. However, numerous recent studies reveal that such models are vulnerable to backdoor attacks. Backdoored NCMs function…

Chain-of-thought (CoT) prompting boosts Large Language Models accuracy on multi-step tasks, yet whether the generated "thoughts" reflect the true internal reasoning process is unresolved. We present the first feature-level causal study of…

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…

Large Reasoning Models (LRMs) achieve strong performance on complex multi-step reasoning, yet they still exhibit severe safety failures such as harmful content generation. Existing methods often apply coarse-grained constraints over the…

Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…

Backdoor attack poses a significant security threat to Deep Learning applications. Existing attacks are often not evasive to established backdoor detection techniques. This susceptibility primarily stems from the fact that these attacks…

Deep learning models are susceptible to {\em backdoor attacks} involving malicious attackers perturbing a small subset of training data with a {\em trigger} to causes misclassifications. Various triggers have been used, including semantic…

Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT…

This is the second in a series of short reports that seek to help business, education, and policy leaders understand the technical details of working with AI through rigorous testing. In this report, we investigate Chain-of-Thought (CoT)…

Chain-of-Thought (CoT) has become a vital technique for enhancing the performance of Large Language Models (LLMs), attracting increasing attention from researchers. One stream of approaches focuses on the iterative enhancement of LLMs by…

Chain-of-Thought (CoT) reasoning has emerged as a powerful tool for enhancing the problem-solving capabilities of large language models (LLMs). However, the theoretical foundations of learning from CoT data remain underdeveloped, and…

Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…

Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training can be vulnerable to poisoning and backdoor attacks by one or…

Recently, ChatGPT has gained significant attention in research due to its ability to interact with humans effectively. The core idea behind this model is reinforcement learning (RL) fine-tuning, a new paradigm that allows language models to…

Recent findings suggest that misaligned models may exhibit deceptive behavior, raising concerns about output trustworthiness. Chain-of-thought (CoT) is a promising tool for alignment monitoring: when models articulate their reasoning…