English
Related papers

Related papers: Detecting Adversarial Fine-tuning with Auditing Ag…

200 papers

Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…

Cryptography and Security · Computer Science 2024-10-23 Xiaohan Fu , Shuheng Li , Zihan Wang , Yihao Liu , Rajesh K. Gupta , Taylor Berg-Kirkpatrick , Earlence Fernandes

Fine-tuning-as-a-service introduces a threat to Large Language Models' safety when service providers fine-tune their models on poisoned user-submitted datasets, a process known as harmful fine-tuning attacks. In this work, we show that by…

Machine Learning · Computer Science 2026-03-03 Quoc Minh Nguyen , Trung Le , Jing Wu , Anh Tuan Bui , Mehrtash Harandi

Safety aligned Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks -- a few harmful data mixed in the fine-tuning dataset can break the LLMs's safety alignment. While several defenses have been proposed, our…

Artificial Intelligence · Computer Science 2025-09-08 Tiansheng Huang , Gautam Bhattacharya , Pratik Joshi , Josh Kimball , Ling Liu

The pretraining and fine-tuning approach has become the leading technique for various NLP applications. However, recent studies reveal that fine-tuning data, due to their sensitive nature, domain-specific characteristics, and…

Computation and Language · Computer Science 2024-11-13 Qian Sun , Hanpeng Wu , Xi Sheryl Zhang

Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing model capabilities, existing text anonymization methods are…

Artificial Intelligence · Computer Science 2025-02-04 Robin Staab , Mark Vero , Mislav Balunović , Martin Vechev

Despite recent efforts in Large Language Model (LLM) safety and alignment, current adversarial attacks on frontier LLMs can still consistently force harmful generations. Although adversarial training has been widely studied and shown to…

Machine Learning · Computer Science 2025-10-29 Csaba Dékány , Stefan Balauca , Robin Staab , Dimitar I. Dimitrov , Martin Vechev

We introduce a defense against adversarial attacks on LLMs utilizing self-evaluation. Our method requires no model fine-tuning, instead using pre-trained models to evaluate the inputs and outputs of a generator model, significantly reducing…

Machine Learning · Computer Science 2024-08-07 Hannah Brown , Leon Lin , Kenji Kawaguchi , Michael Shieh

Phishing detection is a critical cybersecurity task that involves the identification and neutralization of fraudulent attempts to obtain sensitive information, thereby safeguarding individuals and organizations from data breaches and…

Cryptography and Security · Computer Science 2024-08-19 Huilin Wang , Bryan Hooi

As LLM-based agents become increasingly prevalent, backdoors can be implanted into agents through user queries or environment feedback, raising critical concerns regarding safety vulnerabilities. However, backdoor attacks are typically…

Cryptography and Security · Computer Science 2025-10-14 Pengyu Zhu , Zhenhong Zhou , Yuanhe Zhang , Shilinlu Yan , Kun Wang , Sen Su

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

Cryptography and Security · Computer Science 2026-03-03 Zhihang Deng , Jiaping Gui , Weinan Zhang

Standard benchmarks fixate on how well large language model (LLM) agents perform in finance, yet say little about whether they are safe to deploy. We argue that accuracy metrics and return-based scores provide an illusion of reliability,…

General Finance · Quantitative Finance 2025-06-03 Zichen Chen , Jiaao Chen , Jianda Chen , Misha Sra

As benchmarks grow in complexity, many apparent agent failures are not failures of the agent at all - they are failures of the benchmark itself: broken specifications, implicit assumptions, and rigid evaluation scripts that penalize valid…

Computation and Language · Computer Science 2026-04-29 Xinming Tu , Tianze Wang , Yingzhou , Lu , Kexin Huang , Yuanhao Qu , Sara Mostafavi

Modern AI benchmarks operate at a complexity that outpaces traditional verification methods. Tasks authored by domain experts often contain implicit assumptions, incomplete environment specifications, and brittle evaluation logic that human…

Computation and Language · Computer Science 2026-05-27 Junlin Wang , Federico Bianchi , Shang Zhu , Fan Nie , Yongchan Kwon , Bhuwan Dhingra , James Zou

Large Language Model (LLM) agents exhibit remarkable performance across diverse applications by using external tools to interact with environments. However, integrating external tools introduces security risks, such as indirect prompt…

Cryptography and Security · Computer Science 2025-03-05 Qiusi Zhan , Richard Fang , Henil Shalin Panchal , Daniel Kang

Large language models (LLMs) such as ChatGPT have evolved into powerful and ubiquitous tools. Fine-tuning on small datasets allows LLMs to acquire specialized skills for specific tasks efficiently. Although LLMs provide great utility in…

Machine Learning · Computer Science 2025-10-08 Ruoxing Yang

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions…

Artificial Intelligence · Computer Science 2026-05-05 Sheldon Yu , Yingcheng Sun , Hanqing Guo , Julian McAuley , Qianqian Tong

Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…

Machine Learning · Statistics 2019-11-11 Mario Diaz , Peter Kairouz , Jiachun Liao , Lalitha Sankar

Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks…

Computation and Language · Computer Science 2025-11-18 Dongyoon Hahm , Taywon Min , Woogyeol Jin , Kimin Lee

Peer review is essential for maintaining academic quality, but the increasing volume of submissions places a significant burden on reviewers. Large language models (LLMs) offer potential assistance in this process, yet their susceptibility…

Computation and Language · Computer Science 2025-10-10 Tzu-Ling Lin , Wei-Chih Chen , Teng-Fang Hsiao , Hou-I Liu , Ya-Hsin Yeh , Yu Kai Chan , Wen-Sheng Lien , Po-Yen Kuo , Philip S. Yu , Hong-Han Shuai

Impressive progress has been made in automated problem-solving by the collaboration of large language model (LLM) based agents. However, these automated capabilities also open avenues for malicious applications. In this paper, we study a…

Cryptography and Security · Computer Science 2026-04-16 Yuntao Du , Zitao Li , Bolin Ding , Yaliang Li , Hanshen Xiao , Jingren Zhou , Ninghui Li