ARES: Adaptive Red-Teaming and End-To-End Repair of Policy-Reward System

Reinforcement Learning from Human Feedback RLHF is central to aligning Large Language Models LLMs, yet it introduces a critical vulnerability: an imperfect Reward Model RM can become a single point of failure when it fails to penalize unsafe behaviors. While existing red-teaming approaches...

Privacy-Aware Machine Unlearning with SISA for Reinforcement Learning-Based Ransomware Detection

Ransomware detection systems increasingly rely on behavior-based machine learning to address evolving attack strategies. However, emerging privacy compliance, data governance, and responsible AI deployment demand not only accurate detection but also the ability to efficiently remove the influence...

CSLE: A Reinforcement Learning Platform for Autonomous Security Management

Reinforcement learning is a promising approach to autonomous and adaptive security management in networked systems. However, current reinforcement learning solutions for security management are mostly limited to simulation environments and it is unclear how they generalize to operational systems...

Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents

Autonomous AI agents built on open-source runtimes such as OpenClaw expose every available tool to every session by default, regardless of the task. A summarization task receives the same shell execution, subagent spawning, and credential access capabilities as a code deployment task, a 15x...

Asking AI for personal advice is a bad idea, Stanford study shows

Stanford computer scientists just proved what therapists already suspected: AI chatbots will agree with almost anything you say to keep you happy. The researchers caught these systems validating dangerous decisions just to maintain user engagement. That's a worrying development, especially given...

Secure Reinforcement Learning: On Model-Free Detection of Man in the Middle Attacks

We consider the problem of learning-based man-in-the-middle MITM attacks in cyber-physical systems CPS, and extend our previously proposed Bellman Deviation Detection BDD framework for model-free reinforcement learning RL. We refine the standard MDP attack model by allowing the reward function to...

DeepXplain: XAI-Guided Autonomous Defense against Multi-Stage APT Campaigns

Advanced Persistent Threats APTs are stealthy, multi-stage attacks that require adaptive and timely defense. While deep reinforcement learning DRL enables autonomous cyber defense, its decisions are often opaque and difficult to trust in operational environments. This paper presents DeepXplain, a...

Cyber Deception for Mission Surveillance Via Hypergame-Theoretic Deep Reinforcement Learning

Unmanned Aerial Vehicles UAVs are valuable for mission-critical systems like surveillance, rescue, or delivery. Not surprisingly, such systems attract cyberattacks, including Denial-of-Service DoS attacks to overwhelm the resources of mission drones MDs. How can we defend UAV mission systems...

NASimJax: GPU-Accelerated Policy Learning Framework for Penetration Testing

Penetration testing, the practice of simulating cyberattacks to identify vulnerabilities, is a complex sequential decision-making task that is inherently partially observable and features large action spaces. Training reinforcement learning RL policies for this domain faces a fundamental...

PISmith: Reinforcement Learning-Based Red Teaming for Prompt Injection Defenses

Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks remains insufficiently evaluated, potentially creating a false sense of security. In this work, we...

Adversarial Reinforcement Learning for Detecting False Data Injection Attacks in Vehicular Routing

In modern transportation networks, adversaries can manipulate routing algorithms using false data injection attacks, such as simulating heavy traffic with multiple devices running crowdsourced navigation applications, to mislead vehicles toward suboptimal routes and increase congestion. To addres...

SlowBA: An Efficiency Backdoor Attack Towards VLM-Based GUI Agents

Modern vision-language-model VLM based graphical user interface GUI agents are expected not only to execute actions accurately but also to respond to user instructions with low latency. While existing research on GUI-agent security mainly focuses on manipulating action correctness, the security...

TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models

The deployment of Large Reasoning Models LRMs in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought CoT is manipulated to provide a linguistically plausible but logically fallacio...

Blockchain-Enabled Routing for Zero-Trust Low-Altitude Intelligent Networks

Due to the scalability and portability, low-altitude intelligent networks LAINs are essential in various fields such as surveillance and disaster rescue. However, in LAINs, unmanned aerial vehicles UAVs are characterized by the distributed topology and high mobility, thus vulnerable to security...

CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions

The evaluation of Large Language Models LLMs for code generation relies heavily on the quality and robustness of test cases. However, existing benchmarks often lack coverage for subtle corner cases, allowing incorrect solutions to pass. To bridge this gap, we propose CodeHacker, an automated agen...

From SFT to RL: Demystifying the Post-Training Pipeline for LLM-Based Vulnerability Detection

The integration of LLMs into vulnerability detection VD has shifted the field toward interpretable and context-aware analysis. While post-training methods have shown promise in general coding tasks, their systematic application to VD remains underexplored. In this paper, we present the first...

Backdoor Attacks on Contrastive Continual Learning for IoT Systems

The Internet of Things IoT systems increasingly depend on continual learning to adapt to non-stationary environments. These environments can include factors such as sensor drift, changing user behavior, device aging, and adversarial dynamics. Contrastive continual learning CCL combines contrastiv...

StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors

AI-text detectors face a critical robustness challenge: adversarial paraphrasing attacks that preserve semantics while evading detection. We introduce StealthRL, a reinforcement learning framework that stress-tests detector robustness under realistic adversarial conditions. StealthRL trains a...

The Role of Learning in Attacking Intrusion Detection Systems

Recent work on network attacks have demonstrated that ML-based network intrusion detection systems NIDS can be evaded with adversarial perturbations. However, these attacks rely on complex optimizations that have large computational overheads, making them impractical in many real-world settings. ...

SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity

Deep Reinforcement Learning DRL has achieved remarkable success in domains requiring sequential decision-making, motivating its application to cybersecurity problems. However, transitioning DRL from laboratory simulations to bespoke cyber environments can introduce numerous issues. This is furthe...