English
Related papers

Related papers: Red Team Redemption: A Structured Comparison of Op…

200 papers

ML-based malware detection on dynamic analysis reports is vulnerable to both evasion and spurious correlations. In this work, we investigate a specific ML architecture employed in the pipeline of a widely-known commercial antivirus company,…

While state-of-the-art language models have achieved impressive results, they remain susceptible to inference-time adversarial attacks, such as adversarial prompts generated by red teams arXiv:2209.07858. One approach proposed to improve…

Computation and Language · Computer Science 2024-01-12 Steffi Chern , Zhen Fan , Andy Liu

The rapid expansion of research on Large Language Model (LLM) safety and robustness has produced a fragmented and oftentimes buggy ecosystem of implementations, datasets, and evaluation methods. This fragmentation makes reproducibility and…

Artificial Intelligence · Computer Science 2025-11-07 Tim Beyer , Jonas Dornbusch , Jakob Steimle , Moritz Ladenburger , Leo Schwinn , Stephan Günnemann

Post-training Large Language Models requires diverse, high-quality data which is rare and costly to obtain, especially in low resource domains and for multi-turn conversations. Common solutions are crowdsourcing or synthetic generation, but…

In this paper, we propose a new approach called MemLoss to improve the adversarial training of machine learning models. MemLoss leverages previously generated adversarial examples, referred to as 'Memory Adversarial Examples,' to enhance…

Machine Learning · Computer Science 2025-10-13 Soroush Mahdi , Maryam Amirmazlaghani , Saeed Saravani , Zahra Dehghanian

This paper presents an algorithmic framework for learning robust policies in asymmetric imperfect-information games, where the joint reward could depend on the uncertain opponent type (a private information known only to the opponent itself…

Artificial Intelligence · Computer Science 2020-03-05 Macheng Shen , Jonathan P. How

Developers try to evaluate whether an AI system can be misused by adversaries before releasing it; for example, they might test whether a model enables cyberoffense, user manipulation, or bioterrorism. In this work, we show that…

Cryptography and Security · Computer Science 2024-07-03 Erik Jones , Anca Dragan , Jacob Steinhardt

Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can require orders of magnitude additional training time due to high cost…

Machine Learning · Computer Science 2020-07-03 Haizhong Zheng , Ziqi Zhang , Juncheng Gu , Honglak Lee , Atul Prakash

Rigid body dynamics simulators are important tools for the design, analysis and optimization of mechanical systems in a variety of technical and scientific applications. This study examines four different simulation environments (Adams,…

Robotics · Computer Science 2025-12-23 Longxiang Shao , Ulrich Dahmen , Juergen Rossmann

Current evaluations of defenses against prompt attacks in large language model (LLM) applications often overlook two critical factors: the dynamic nature of adversarial behavior and the usability penalties imposed on legitimate users by…

Cyber defence exercises are intensive, hands-on learning events for teams of professionals who gain or develop their skills to successfully prevent and respond to cyber attacks. The exercises mimic the real-life, routine operation of an…

Cryptography and Security · Computer Science 2017-12-29 Jan Vykopal , Radek Ošlejšek , Karolína Burská , Kristína Zákopčanová

Machine learning techniques are currently used extensively for automating various cybersecurity tasks. Most of these techniques utilize supervised learning algorithms that rely on training the algorithm to classify incoming data into…

Cryptography and Security · Computer Science 2019-12-06 Prithviraj Dasgupta , Joseph B. Collins

As large language models (LLMs) are increasingly deployed as black-box components in real-world applications, red teaming has become essential for identifying potential risks. It tests LLMs with adversarial prompts to uncover…

Machine Learning · Computer Science 2026-03-25 Jiale Ding , Xiang Zheng , Yutao Wu , Cong Wang , Wei-Bin Lee , Ling Pan , Xingjun Ma , Yu-Gang Jiang

Recent progress in the field of reinforcement learning has been accelerated by virtual learning environments such as video games, where novel algorithms and ideas can be quickly tested in a safe and reproducible manner. We introduce the…

As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…

Machine Learning · Computer Science 2025-02-06 Chen Henry Wu , Rishi Shah , Jing Yu Koh , Ruslan Salakhutdinov , Daniel Fried , Aditi Raghunathan

As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect and mitigate risks. Large Language Models (LLMs) offer promising capabilities for enhancing threat…

Cryptography and Security · Computer Science 2025-05-20 Xiaoqun Liu , Feiyang Yu , Xi Li , Guanhua Yan , Ping Yang , Zhaohan Xi

This paper presents a controlled study of adversarial reinforcement learning in network security through a custom OpenAI Gym environment that models brute-force attacks and reactive defenses on multi-port services. The environment captures…

Machine Learning · Computer Science 2025-10-08 Abrar Shahid , Ibteeker Mahir Ishum , AKM Tahmidul Haque , M Sohel Rahman , A. B. M. Alim Al Islam

As the number and complexity of malware attacks continue to increase, there is an urgent need for effective malware detection systems. While deep learning models are effective at detecting malware, they are vulnerable to adversarial…

Cryptography and Security · Computer Science 2023-12-18 Mahesh Datta Sai Ponnuru , Likhitha Amasala , Tanu Sree Bhimavarapu , Guna Chaitanya Garikipati

Cyber attacks are ubiquitous and a constantly growing threat in the age of digitization. In order to protect important data, developers and system administrators must be trained and made aware of possible threats. Practical training can be…

Cryptography and Security · Computer Science 2024-07-24 Andreas Eipper , Daniela Pöhn

Reinforcement learning based dialogue policies are typically trained in interaction with a user simulator. To obtain an effective and robust policy, this simulator should generate user behaviour that is both realistic and varied. Current…

Computation and Language · Computer Science 2023-06-02 Simon Keizer , Caroline Dockes , Norbert Braunschweiler , Svetlana Stoyanchev , Rama Doddipatla