English
Related papers

Related papers: Weakest Link in the Chain: Security Vulnerabilitie…

200 papers

Recent years have witnessed significant progress in large language models' (LLMs) reasoning, which is largely due to the chain-of-thought (CoT) approaches, allowing models to generate intermediate reasoning steps before reaching the final…

Computation and Language · Computer Science 2025-04-15 Zuoli Tang , Junjie Ou , Kaiqin Hu , Chunwei Wu , Zhaoxin Huan , Chilin Fu , Xiaolu Zhang , Jun Zhou , Chenliang Li

The rapid development of large reasoning models (LRMs), such as OpenAI-o3 and DeepSeek-R1, has led to significant improvements in complex reasoning over non-reasoning large language models~(LLMs). However, their enhanced capabilities,…

Computers and Society · Computer Science 2025-11-18 Kaiwen Zhou , Chengzhi Liu , Xuandong Zhao , Shreedhar Jangam , Jayanth Srinivasa , Gaowen Liu , Dawn Song , Xin Eric Wang

Hundreds of defenses have been proposed to make deep neural networks robust against minimal (adversarial) input perturbations. However, only a handful of these defenses held up their claims because correctly evaluating robustness is…

Machine Learning · Computer Science 2022-06-29 Roland S. Zimmermann , Wieland Brendel , Florian Tramer , Nicholas Carlini

Reasoning language models improve performance on complex tasks by generating long chains of thought (CoTs), but this process can also increase harmful outputs in adversarial settings. In this work, we ask whether the long CoTs can be…

Computation and Language · Computer Science 2025-10-08 Yik Siu Chan , Zheng-Xin Yong , Stephen H. Bach

Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings…

Machine Learning · Statistics 2019-09-06 Aleksander Madry , Aleksandar Makelov , Ludwig Schmidt , Dimitris Tsipras , Adrian Vladu

As the pre-trained language models (PLMs) continue to grow, so do the hardware and data requirements for fine-tuning PLMs. Therefore, the researchers have come up with a lighter method called \textit{Prompt Learning}. However, during the…

Computation and Language · Computer Science 2022-09-07 Yundi Shi , Piji Li , Changchun Yin , Zhaoyang Han , Lu Zhou , Zhe Liu

Recently, Zaremba et al. demonstrated that increasing inference-time computation improves robustness in large proprietary reasoning LLMs. In this paper, we first show that smaller-scale, open-source models (e.g., DeepSeek R1, Qwen3,…

Artificial Intelligence · Computer Science 2025-07-23 Tong Wu , Chong Xiang , Jiachen T. Wang , Weichen Yu , Chawin Sitawarin , Vikash Sehwag , Prateek Mittal

The growing use of Large Language Models (LLMs) for automated code generation has enhanced software development efficiency, but often at the cost of security. Generated code frequently overlooks critical concerns, leaving it vulnerable to…

Cryptography and Security · Computer Science 2026-05-26 Mohammed Kharma , Ahmed Sabbah , Mohammad Alkhanafseh , Mohammad Hammoudeh , David Mohaisen

Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law…

Machine Learning · Computer Science 2026-03-20 Xiangwen Wang , Ananth Balashankar , Varun Chandrasekaran

We present a novel framework addressing a critical vulnerability in Large Language Models (LLMs): the prevalence of factual inaccuracies within intermediate reasoning steps despite correct final answers. This phenomenon poses substantial…

Computation and Language · Computer Science 2025-08-05 Rui Jiao , Yue Zhang , Jinku Li

Large language models increasingly rely on explicit chain-of-thought reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work focuses predominantly on content safety (i.e.,…

Artificial Intelligence · Computer Science 2026-05-07 Xunguang Wang , Yuguang Zhou , Qingyue Wang , Zongjie Li , Ruixuan Huang , Zhenlan Ji , Pingchuan Ma , Shuai Wang

We study the task of prompting large-scale language models to perform multi-step reasoning. Existing work shows that when prompted with a chain of thoughts (CoT), sequences of short sentences describing intermediate reasoning steps towards…

Computation and Language · Computer Science 2023-01-31 Yao Fu , Hao Peng , Ashish Sabharwal , Peter Clark , Tushar Khot

Rationalization models, which select a subset of input text as rationale-crucial for humans to understand and trust predictions-have recently emerged as a prominent research area in eXplainable Artificial Intelligence. However, most of…

Computation and Language · Computer Science 2024-09-20 Yuankai Zhang , Lingxiao Kong , Haozhao Wang , Ruixuan Li , Jun Wang , Yuhua Li , Wei Liu

Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturbations has moved from a peculiar phenomenon to a core issue in Deep Learning. Despite much attention, however, progress towards more robust…

Machine Learning · Statistics 2019-12-13 Wieland Brendel , Jonas Rauber , Matthias Kümmerer , Ivan Ustyuzhaninov , Matthias Bethge

Nowadays, we are more and more reliant on Deep Learning (DL) models and thus it is essential to safeguard the security of these systems. This paper explores the security issues in Deep Learning and analyses, through the use of experiments,…

Machine Learning · Computer Science 2022-04-26 Marco Marchetti , Edmond S. L. Ho

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Cryptography and Security · Computer Science 2023-07-28 Nikhil Kandpal , Matthew Jagielski , Florian Tramèr , Nicholas Carlini

Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Levente Halmosi , Bálint Mohos , Márk Jelasity

Large language model performance can be improved in a large number of ways. Many such techniques, like fine-tuning or advanced tool usage, are time-intensive and expensive. Although prompt engineering is significantly cheaper and often…

Computation and Language · Computer Science 2025-06-03 Philipp Schoenegger , Cameron R. Jones , Philip E. Tetlock , Barbara Mellers

Reasoning-based language models have demonstrated strong performance across various domains, with the most notable gains seen in mathematical and coding tasks. Recent research has shown that reasoning also offers significant benefits for…

Artificial Intelligence · Computer Science 2025-05-27 Makesh Narsimhan Sreedhar , Traian Rebedea , Christopher Parisien

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

Computation and Language · Computer Science 2024-11-11 Md Abdur Rahman , Fan Wu , Alfredo Cuzzocrea , Sheikh Iqbal Ahamed