相关论文: Farsighted Risk Mitigation of Lateral Movement Usi…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Detection of malicious behavior is a fundamental problem in security. One of the major challenges in using detection systems in practice is in dealing with an overwhelming number of alerts that are triggered by normal behavior (the…

A recent defense proposes to inject "honeypots" into neural networks in order to detect adversarial attacks. We break the baseline version of this defense by reducing the detection true positive rate to 0\% and the detection AUC to 0.02,…

Large language models increasingly rely on explicit chain-of-thought reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work focuses predominantly on content safety (i.e.,…

In this paper we describe an algorithm for predicting the websites at risk in a long range hacking activity, while jointly inferring the provenance and evolution of vulnerabilities on websites over continuous time. Specifically, we use…

Information systems enable many organizational processes in every industry. The efficiencies and effectiveness in the use of information technologies create an unintended byproduct: misuse by existing users or somebody impersonating them -…

This paper addresses the online motion planning problem of mobile robots under complex high-level tasks. The robot motion is modeled as an uncertain Markov Decision Process (MDP) due to limited initial knowledge, while the task is specified…

This paper studies the deployment of joint moving target defense (MTD) and deception against multi-stage cyberattacks. Given the system equipped with MTD that randomizes between different configurations, we investigate how to allocate a…

Dynamic routing is one of the representative control scheme in transportation, production lines, and data transmission. In the modern context of connectivity and autonomy, routing decisions are potentially vulnerable to malicious attacks.…

Security issues in MANET are a challenging task nowadays. MANETs are vulnerable to passive attacks and active attacks because of a limited number of resources and lack of centralized authority. Blackhole attack is an attack in network layer…

Federated learning is a versatile framework for training models in decentralized environments. However, the trust placed in clients makes federated learning vulnerable to backdoor attacks launched by malicious participants. While many…

Autonomous UAV navigation using reinforcement learning (RL) is vulnerable to adversarial attacks that manipulate sensor inputs, potentially leading to unsafe behavior and mission failure. Although robust RL methods provide partial…

Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or…

As LLM-driven agents advance in cybersecurity, Jeopardy CTF benchmarks are approaching saturation and cyber ranges, the natural next evaluation frontier, offer diminishing resistance under their current static design. We validate this…

Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulnerable to jailbreak attacks that bypass safety guardrails.…

Advanced Persistent Threats (APTs) have created new security challenges for critical infrastructures due to their stealthy, dynamic, and adaptive natures. In this work, we aim to lay a game-theoretic foundation by establishing a multi-stage…

Motion planning of an autonomous system with high-level specifications has wide applications. However, research of formal languages involving timed temporal logic is still under investigation. Furthermore, many existing results rely on a…

In a typical stochastic multi-armed bandit problem, the objective is often to maximize the expected sum of rewards over some time horizon $T$. While the choice of a strategy that accomplishes that is optimal with no additional information,…

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

When large language model (LLM) systems interact with external data to perform complex tasks, a new attack, namely prompt injection, becomes a significant threat. By injecting instructions into the data accessed by the system, the attacker…