English
Related papers

Related papers: Reasoning Introduces New Poisoning Attacks Yet Mak…

200 papers

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the…

Machine Learning · Computer Science 2023-10-31 Ruixiang Tang , Jiayi Yuan , Yiming Li , Zirui Liu , Rui Chen , Xia Hu

Large language models (LLMs) have gained human trust due to their capabilities and helpfulness. However, this in turn may allow LLMs to affect users' mindsets by manipulating language. It is termed as gaslighting, a psychological effect. In…

Cryptography and Security · Computer Science 2024-10-15 Wei Li , Luyao Zhu , Yang Song , Ruixi Lin , Rui Mao , Yang You

Large language models (LLMs) excel at complex reasoning but can still exhibit harmful behaviors. Current alignment strategies typically embed safety into model weights, making these controls implicit, static, and difficult to modify. This…

Computation and Language · Computer Science 2025-10-15 Xuanming Zhang , Yuxuan Chen , Samuel Yeh , Sharon Li

With the development of natural language processing (NLP), large language models (LLMs) are becoming increasingly popular. LLMs are integrating more into everyday life, raising public concerns about their security vulnerabilities.…

Computation and Language · Computer Science 2024-06-27 Ziqiu Wang , Jun Liu , Shengkai Zhang , Yang Yang

Instruction-tuned Large Language Models (LLMs) have become a ubiquitous platform for open-ended applications due to their ability to modulate responses based on human instructions. The widespread use of LLMs holds significant potential for…

Computation and Language · Computer Science 2024-04-04 Jun Yan , Vikas Yadav , Shiyang Li , Lichang Chen , Zheng Tang , Hai Wang , Vijay Srinivasan , Xiang Ren , Hongxia Jin

Large Language Models (LLMs) significantly benefit from Chain-of-Thought (CoT) prompting in performing various reasoning tasks. While CoT allows models to produce more comprehensive reasoning processes, its emphasis on intermediate…

Computation and Language · Computer Science 2023-10-05 Zhan Ling , Yunhao Fang , Xuanlin Li , Zhiao Huang , Mingu Lee , Roland Memisevic , Hao Su

The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which…

Cryptography and Security · Computer Science 2025-10-15 Dominik Schwarz

Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems, but remains constrained by the computational cost and reasoning path collapse when grounded in discrete token spaces. Recent latent reasoning…

Artificial Intelligence · Computer Science 2026-02-05 Jiecong Wang , Hao Peng , Chunyang Liu

Adversarial attacks alter NLP model predictions by perturbing test-time inputs. However, it is much less understood whether, and how, predictions can be manipulated with small, concealed changes to the training data. In this work, we…

Computation and Language · Computer Science 2021-04-13 Eric Wallace , Tony Z. Zhao , Shi Feng , Sameer Singh

As Large Language Models (LLMs) are increasingly being employed in real-world applications in critical domains such as healthcare, it is important to ensure that the Chain-of-Thought (CoT) reasoning generated by these models faithfully…

Computation and Language · Computer Science 2024-07-02 Sree Harsha Tanneru , Dan Ley , Chirag Agarwal , Himabindu Lakkaraju

In the domain of large language models (LLMs), in-context learning (ICL) has been recognized for its innovative ability to adapt to new tasks, relying on examples rather than retraining or fine-tuning. This paper delves into the critical…

Cryptography and Security · Computer Science 2025-06-03 Pengfei He , Han Xu , Yue Xing , Hui Liu , Makoto Yamada , Jiliang Tang

The development of Long-CoT reasoning has advanced LLM performance across various tasks, including language understanding, complex problem solving, and code generation. This paradigm enables models to generate intermediate reasoning steps,…

Computation and Language · Computer Science 2025-09-05 Yanbo Wang , Yongcan Yu , Jian Liang , Ran He

Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…

Machine Learning · Computer Science 2025-10-21 Bingqi Shang , Yiwei Chen , Yihua Zhang , Bingquan Shen , Sijia Liu

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

Computation and Language · Computer Science 2025-06-13 Jaechul Roh , Varun Gandhi , Shivani Anilkumar , Arin Garg

Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in causal language models. Our approach relies on two key…

Cryptography and Security · Computer Science 2026-02-04 Blake Bullwinkel , Giorgio Severi , Keegan Hines , Amanda Minnich , Ram Shankar Siva Kumar , Yonatan Zunger

Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…

Cryptography and Security · Computer Science 2022-10-20 Yangyi Chen , Fanchao Qi , Hongcheng Gao , Zhiyuan Liu , Maosong Sun

Latent tokens are gaining attention for enhancing reasoning in large language models (LLMs), yet their internal mechanisms remain unclear. This paper examines the problem from a reliability perspective, uncovering fundamental weaknesses:…

Computation and Language · Computer Science 2025-12-29 Yuyi Zhang , Boyu Tang , Tianjie Ju , Sufeng Duan , Gongshen Liu

Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs). CoT explicitly encourages the LLM to generate intermediate rationales for solving a problem, by providing a series…

Computation and Language · Computer Science 2023-06-02 Boshi Wang , Sewon Min , Xiang Deng , Jiaming Shen , You Wu , Luke Zettlemoyer , Huan Sun

Chain-of-thought (CoT) prompting is a de-facto standard technique to elicit reasoning-like responses from large language models (LLMs), allowing them to spell out individual steps before giving a final answer. While the resemblance to…

Artificial Intelligence · Computer Science 2026-02-26 Gregor Bachmann , Yichen Jiang , Seyed Mohsen Moosavi Dezfooli , Moin Nabi

Deep learning models have recently shown to be vulnerable to backdoor poisoning, an insidious attack where the victim model predicts clean images correctly but classifies the same images as the target class when a trigger poison pattern is…

Computer Vision and Pattern Recognition · Computer Science 2019-11-20 Alvin Chan , Yew-Soon Ong