English
Related papers

Related papers: Feature-Aware Malicious Output Detection and Mitig…

200 papers

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Computation and Language · Computer Science 2023-11-30 Jiaxin Wen , Pei Ke , Hao Sun , Zhexin Zhang , Chengfei Li , Jinfeng Bai , Minlie Huang

Large language models (LLMs) offer promising opportunities for organizational research. However, their built-in moderation systems can create problems when researchers try to analyze harmful content, often refusing to follow certain…

Artificial Intelligence · Computer Science 2025-06-23 Mustafa Akben , Aaron Satko

Large language models (LLMs) have become ubiquitous, thus it is important to understand their risks and limitations. Smaller LLMs can be deployed where compute resources are constrained, such as edge devices, but with different propensity…

Computation and Language · Computer Science 2025-04-22 Berk Atil , Vipul Gupta , Sarkar Snigdha Sarathi Das , Rebecca J. Passonneau

We introduce FreqRank, a mutation-based defense to localize malicious components in LLM outputs and their corresponding backdoor triggers. FreqRank assumes that the malicious sub-string(s) consistently appear in outputs for triggered inputs…

Cryptography and Security · Computer Science 2025-09-23 Mayukh Borana , Junyi Liang , Sai Sathiesh Rajan , Sudipta Chattopadhyay

The rapid evolution of malware variants requires robust classification methods to enhance cybersecurity. While Large Language Models (LLMs) offer potential for generating malware descriptions to aid family classification, their utility is…

Cryptography and Security · Computer Science 2025-05-01 Ivan Montoya Sanchez , Shaswata Mitra , Aritran Piplai , Sudip Mittal

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes…

Cryptography and Security · Computer Science 2026-01-28 Yangyang Guo , Ziwei Xu , Si Liu , Zhiming Zheng , Mohan Kankanhalli

Federated learning systems are vulnerable to attacks from malicious clients. As the central server in the system cannot govern the behaviors of the clients, a rogue client may initiate an attack by sending malicious model updates to the…

Machine Learning · Computer Science 2020-02-04 Suyi Li , Yong Cheng , Wei Wang , Yang Liu , Tianjian Chen

Stealthy data poisoning during fine-tuning can backdoor large language models (LLMs), threatening downstream safety. Existing detectors either use classifier-style probability signals--ill-suited to generation--or rely on rewriting, which…

Computation and Language · Computer Science 2025-11-13 Jinwen Chen , Hainan Zhang , Fei Sun , Qinnan Zhang , Sijia Wen , Ziwei Wang , Zhiming Zheng

The representation of feature space is a crucial environment where data points get vectorized and embedded for subsequent modeling. Thus the efficacy of machine learning (ML) algorithms is closely related to the quality of feature…

Machine Learning · Computer Science 2026-01-12 Xinhao Zhang , Jinghan Zhang , Banafsheh Rekabdar , Yuanchun Zhou , Pengfei Wang , Kunpeng Liu

Most prior safety research of large language models (LLMs) has focused on enhancing the alignment of LLMs to better suit the safety requirements of humans. However, internalizing such safeguard features into larger models brought challenges…

Computation and Language · Computer Science 2025-01-24 Ohjoon Kwon , Donghyeon Jeon , Nayoung Choi , Gyu-Hwung Cho , Changbong Kim , Hyunwoo Lee , Inho Kang , Sun Kim , Taiwoo Park

Large language models (LLMs) excel in many diverse applications beyond language generation, e.g., translation, summarization, and sentiment analysis. One intriguing application is in text classification. This becomes pertinent in the realm…

Computation and Language · Computer Science 2024-03-14 Tharindu Kumarage , Amrita Bhattacharjee , Joshua Garland

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the…

Computation and Language · Computer Science 2025-10-06 Zhe Li , Wei Zhao , Yige Li , Jun Sun

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Cryptography and Security · Computer Science 2026-05-22 Shahnewaz Karim Sakib , Swati Kar , Anindya Bijoy Das

We find that language models have difficulties generating fallacious and deceptive reasoning. When asked to generate deceptive outputs, language models tend to leak honest counterparts but believe them to be false. Exploiting this…

Computation and Language · Computer Science 2025-05-26 Yue Zhou , Henry Peng Zou , Barbara Di Eugenio , Yang Zhang

Large language models (LLMs) have transformed human writing by enhancing grammar correction, content expansion, and stylistic refinement. However, their widespread use raises concerns about authorship, originality, and ethics, even…

Computation and Language · Computer Science 2024-10-21 Zhen Tao , Zhiyu Li , Runyu Chen , Dinghao Xi , Wei Xu

Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem. However, existing methods for mitigating over-refusal cannot maintain a low refusal ratio for harmless queries…

Computation and Language · Computer Science 2026-04-21 Yupeng Qi , Ziyu Lyu , Lixin Cui , Lu Bai , Feng Xia

Large language models demonstrate powerful capabilities across various natural language processing tasks, yet they also harbor safety vulnerabilities. To enhance LLM safety, various jailbreak defense methods have been proposed to guard…

Cryptography and Security · Computer Science 2025-11-25 Junbo Zhang , Ran Chen , Qianli Zhou , Xinyang Deng , Wen Jiang

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not only frustrate users but also provoke a public backlash…

Computation and Language · Computer Science 2025-06-12 Bang An , Sicheng Zhu , Ruiyi Zhang , Michael-Andrei Panaitescu-Liess , Yuancheng Xu , Furong Huang

The widespread adoption of Large Language Models (LLMs) in critical applications has introduced severe reliability and security risks, as LLMs remain vulnerable to notorious threats such as hallucinations, jailbreak attacks, and backdoor…

Cryptography and Security · Computer Science 2026-04-07 Shide Zhou , Kailong Wang , Ling Shi , Haoyu Wang

Feature selection (FS) remains essential for building accurate and interpretable detection models, particularly in high-dimensional malware datasets. Conventional FS methods such as Extra Trees, Variance Threshold, Tree-based models,…

Machine Learning · Computer Science 2026-02-11 Naveen Gill , Ajvad Haneef K , Madhu Kumar S D