English
Related papers

Related papers: Chasing Moving Targets with Online Self-Play Reinf…

200 papers

The rapid advancement of large language models (LLMs) has increased the need for guardrail models to ensure responsible use, particularly in detecting unsafe and illegal content. While substantial safety data exist in English, multilingual…

Computation and Language · Computer Science 2025-02-10 Yihe Deng , Yu Yang , Junkai Zhang , Wei Wang , Bo Li

Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…

Cryptography and Security · Computer Science 2026-01-26 Xianya Fang , Xianying Luo , Yadong Wang , Xiang Chen , Yu Tian , Zequn Sun , Rui Liu , Jun Fang , Naiqiang Tan , Yuanning Cui , Sheng-Jun Huang

Network systems often contain vulnerabilities that remain unfixed in a network for various reasons, such as the lack of a patch or knowledge to fix them. With the presence of such residual vulnerabilities, the network administrator should…

Cryptography and Security · Computer Science 2022-11-04 Narges Khakpour , David Parker

Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…

Machine Learning · Computer Science 2024-02-06 Xinglong Zhang , Yaoqian Peng , Biao Luo , Wei Pan , Xin Xu , Haibin Xie

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…

Computation and Language · Computer Science 2024-06-25 Simone Tedeschi , Felix Friedrich , Patrick Schramowski , Kristian Kersting , Roberto Navigli , Huu Nguyen , Bo Li

Malicious attackers can exploit large language models (LLMs) by engaging them in multi-turn dialogues to achieve harmful objectives, posing significant safety risks to society. To address this challenge, we propose a novel defense…

Reinforcement learning (RL) has been demonstrated suitable to develop agents that play complex games with human-level performance. However, it is not understood how to effectively use RL to perform cybersecurity tasks. To develop such…

Cryptography and Security · Computer Science 2021-03-16 Andres Molina-Markham , Cory Miniter , Becky Powell , Ahmad Ridley

Fine-tuning large language models (LLMs) on telecom datasets is a common practice to adapt general-purpose models to the telecom domain. However, little attention has been paid to how this process may compromise model safety. Recent…

Computers and Society · Computer Science 2026-02-09 Aladin Djuhera , Swanand Ravindra Kadhe , Farhan Ahmed , Syed Zawad , Fernando Koch , Walid Saad , Holger Boche

Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and tool execution. While these capabilities unlock substantial practical value, they also introduce…

Cryptography and Security · Computer Science 2026-05-25 Zhe Liu , Zonghao Ying , Wenxin Zhang , Quanchen Zou , Deyue Zhang , Dongdong Yang , Xiangzheng Zhang , Hao Peng

Reinforcement Learning (RL) agents often struggle with inefficient exploration, particularly in environments with sparse rewards. Traditional exploration strategies can lead to slow learning and suboptimal performance because agents fail to…

Machine Learning · Computer Science 2026-03-31 Gaurav Chaudhary , Laxmidhar Behera , Washim Uddin Mondal

As large language models (LLMs) grow more capable, concerns about their safe deployment have also grown. Although alignment mechanisms have been introduced to deter misuse, they remain vulnerable to carefully designed adversarial prompts.…

Computation and Language · Computer Science 2025-08-19 Xinbo Wu , Abhishek Umrawal , Lav R. Varshney

We investigate learning the equilibria in non-stationary multi-agent systems and address the challenges that differentiate multi-agent learning from single-agent learning. Specifically, we focus on games with bandit feedback, where testing…

Machine Learning · Computer Science 2024-05-06 Haozhe Jiang , Qiwen Cui , Zhihan Xiong , Maryam Fazel , Simon S. Du

Fine-tuning large language models (LLMs) for alignment typically relies on supervised fine-tuning or reinforcement learning from human feedback, both limited by the cost and scarcity of high-quality annotations. Recent self-play and…

Machine Learning · Computer Science 2026-02-03 Shiguang Wu , Yaqing Wang , Quanming Yao

We motivate and propose a new model for non-cooperative Markov game which considers the interactions of risk-aware players. This model characterizes the time-consistent dynamic "risk" from both stochastic state transitions (inherent to the…

Computer Science and Game Theory · Computer Science 2019-11-22 Wenjie Huang , Pham Viet Hai , William B. Haskell

In this paper, we investigate a competitive market involving two agents who consider both their own wealth and the wealth gap with their opponent. Both agents can invest in a financial market consisting of a risk-free asset and a risky…

Optimization and Control · Mathematics 2025-02-10 Junyi Guo , Xia Han , Hao Wang , Kam Chuen Yuen

Language Models (LMs) often cannot be deployed because of their potential to harm users in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write test cases. However, human…

Computation and Language · Computer Science 2022-02-08 Ethan Perez , Saffron Huang , Francis Song , Trevor Cai , Roman Ring , John Aslanides , Amelia Glaese , Nat McAleese , Geoffrey Irving

The rapid advancement of multimodal large language models (MLLMs) has led to breakthroughs in various applications, yet their security remains a critical challenge. One pressing issue involves unsafe image-query pairs--jailbreak inputs…

Cryptography and Security · Computer Science 2025-07-30 Muzhi Dai , Shixuan Liu , Zhiyuan Zhao , Junyu Gao , Hao Sun , Xuelong Li

Extensive efforts have been made before the public release of Large language models (LLMs) to align their behaviors with human values. However, even meticulously aligned LLMs remain vulnerable to malicious manipulations such as…

Cryptography and Security · Computer Science 2024-10-01 Zeguan Xiao , Yan Yang , Guanhua Chen , Yun Chen

The prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive usage of LLMs, recent works have proposed algorithms to…

Computation and Language · Computer Science 2023-10-20 Zhouxing Shi , Yihan Wang , Fan Yin , Xiangning Chen , Kai-Wei Chang , Cho-Jui Hsieh

We study automated intrusion response and formulate the interaction between an attacker and a defender as an optimal stopping game where attack and defense strategies evolve through reinforcement learning and self-play. The game-theoretic…

Computer Science and Game Theory · Computer Science 2024-04-23 Kim Hammar , Rolf Stadler