English
Related papers

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

200 papers

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Computation and Language · Computer Science 2026-02-02 Anindya Sundar Das , Kangjie Chen , Monowar Bhuyan

Chain-of-thought (CoT) prompting has been widely adopted to enhance the reasoning capabilities of large language models (LLMs). However, the effectiveness of CoT reasoning is inconsistent across tasks with different reasoning types. This…

Machine Learning · Computer Science 2025-06-17 Yue Wan , Xiaowei Jia , Xiang Lorraine Li

Large Reasoning Models (LRMs) have significantly improved problem-solving through explicit Chain-of-Thought (CoT) reasoning. However, this capability creates a Safety-Helpfulness Paradox: the reasoning process itself can be misused to…

Artificial Intelligence · Computer Science 2026-01-27 Xin Gao , Shaohan Yu , Zerui Chen , Yueming Lyu , Weichen Yu , Guanghao Li , Jiyao Liu , Jianxiong Gao , Jian Liang , Ziwei Liu , Chenyang Si

With the widespread application of large language models in code generation, recent studies demonstrate that employing additional Chain-of-Thought generation models can significantly enhance code generation performance by providing explicit…

Software Engineering · Computer Science 2025-08-13 Naizhu Jin , Zhong Li , Tian Zhang , Qingkai Zeng

Language Models (LMs) emit Chains-of-Thought (CoTs) that drive much of their capability. However, the same sequence that carries useful reasoning can also covertly convey messages: a misaligned model may embed covert information in its CoT…

Computation and Language · Computer Science 2026-05-27 Zhejian Zhou , Jonathan May

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…

Computation and Language · Computer Science 2024-11-28 Chen Chen , Yuchen Sun , Xueluan Gong , Jiaxin Gao , Kwok-Yan Lam

Large Reasoning Models (LRMs) have significantly advanced beyond traditional Large Language Models (LLMs) with their exceptional logical reasoning capabilities, yet these improvements introduce heightened safety risks. When subjected to…

Cryptography and Security · Computer Science 2025-06-04 Yang Yao , Xuan Tong , Ruofan Wang , Yixu Wang , Lujundong Li , Liang Liu , Yan Teng , Yingchun Wang

Chain-of-thought (CoT) reasoning is useful for monitoring language models only when the reasoning trace faithfully reflects the computation that produces the final answer. However, models can rely on prompt-to-answer shortcuts that bypass…

Machine Learning · Computer Science 2026-05-26 Jinghan Jia , Joe Benton , Eric Easley

Despite the remarkable successes of large language models (LLMs), the underlying Transformer architecture has inherent limitations in handling complex reasoning tasks. Chain-of-thought (CoT) prompting has emerged as a practical workaround,…

Computation and Language · Computer Science 2025-06-03 Xiang Zhang , Juntai Cao , Jiaqi Wei , Chenyu You , Dujian Ding

Chain-of-Thought (CoT) prompting can effectively elicit complex multi-step reasoning from Large Language Models~(LLMs). For example, by simply adding CoT instruction ``Let's think step-by-step'' to each input query of MultiArith dataset,…

Artificial Intelligence · Computer Science 2023-04-19 Jiuhai Chen , Lichang Chen , Heng Huang , Tianyi Zhou

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Cryptography and Security · Computer Science 2025-10-08 Guangyu Shen , Siyuan Cheng , Xiangzhe Xu , Yuan Zhou , Hanxi Guo , Zhuo Zhang , Xiangyu Zhang

Deep learning models are vulnerable to backdoor attacks, where adversaries inject malicious functionality during training that activates on trigger inputs at inference time. Extensive research has focused on developing stealthy backdoor…

Cryptography and Security · Computer Science 2024-11-26 Jeongjin Shin , Sangdon Park

The success of deep learning has enabled advances in multimodal tasks that require non-trivial fusion of multiple input domains. Although multimodal models have shown potential in many problems, their increased complexity makes them more…

Computer Vision and Pattern Recognition · Computer Science 2022-04-20 Matthew Walmer , Karan Sikka , Indranil Sur , Abhinav Shrivastava , Susmit Jha

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that…

Cryptography and Security · Computer Science 2025-06-17 Mengyuan Sun , Yu Li , Yuchen Liu , Bo Du , Yunjie Ge

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…

Cryptography and Security · Computer Science 2026-01-06 Eric Xue , Ruiyi Zhang , Pengtao Xie

Adversaries can embed backdoors in deep learning models by introducing backdoor poison samples into training datasets. In this work, we investigate how to detect such poison samples to mitigate the threat of backdoor attacks. First, we…

Machine Learning · Computer Science 2023-06-21 Xiangyu Qi , Tinghao Xie , Jiachen T. Wang , Tong Wu , Saeed Mahloujifar , Prateek Mittal

Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question, but it is unclear if the stated reasoning is a faithful explanation of the model's actual reasoning…

Deep reinforcement learning (DRL) has made significant achievements in many real-world applications. But these real-world applications typically can only provide partial observations for making decisions due to occlusions and noisy sensors.…

Machine Learning · Computer Science 2022-12-13 Yinbo Yu , Jiajia Liu , Shouqing Li , Kepu Huang , Xudong Feng

Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…

Computation and Language · Computer Science 2024-10-22 Yihua Zhou , Xiaochuan Shi

Chain-of-Thought (CoT) prompting has significantly enhanced the mathematical reasoning capabilities of Large Language Models. We find existing fine-tuning datasets frequently suffer from the "answer right but reasoning wrong" probelm, where…

Artificial Intelligence · Computer Science 2026-01-13 Zihang Li , Yuhang Wang , Yikun Zong , Wenhan Yu , Xiaokun Yuan , Runhan Jiang , Zirui Liu , Tong Yang , Arthur Jiang