相关论文: Aim Low, Shoot High: Evading Aimbot Detectors by M…

For over a decade, cybersecurity has relied on human labor scarcity to limit attackers to high-value targets manually or generic automated attacks at scale. Building sophisticated exploits requires deep expertise and manual effort, leading…

Attacks exploiting the innate and the acquired vulnerabilities of human users have posed severe threats to cybersecurity. This work proposes ADVERT, a human-technical solution that generates adaptive visual aids in real-time to prevent…

This paper introduces a novel application of Supervised Contrastive Learning (SupCon) to Imitation Learning (IL), with a focus on learning more effective state representations for agents in video game environments. The goal is to obtain…

Can machine learning models for recommendation be easily fooled? While the question has been answered for hand-engineered fake user profiles, it has not been explored for machine learned adversarial attacks. This paper attempts to close…

The increasing use of Artificial Intelligence (AI) technologies, such as Large Language Models (LLMs) has led to nontrivial improvements in various tasks, including accurate authorship identification of documents. However, while LLMs…

Large language models (LLMs) aligned for safety through techniques like reinforcement learning from human feedback (RLHF) often exhibit emergent deceptive behaviors, where outputs appear compliant but subtly mislead or omit critical…

Deceptive patterns in digital interfaces manipulate users into making unintended decisions, exploiting cognitive biases and psychological vulnerabilities. These patterns have become ubiquitous on various digital platforms. While efforts to…

Due to the broad range of applications of stochastic multi-armed bandit model, understanding the effects of adversarial attacks and designing bandit algorithms robust to attacks are essential for the safe applications of this model. In this…

Cybersecurity practices require effort to be maintained, and one weakness is a lack of awareness regarding potential attacks not only in the usage of machine learning models, but also in their development process. Previous studies have…

AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly…

It is now common to evaluate Large Language Models (LLMs) by having humans manually vote to evaluate model outputs, in contrast to typical benchmarks that evaluate knowledge or skill at some particular task. Chatbot Arena, the most popular…

Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their…

Security challenges accompany the efficiency. The pervasive integration of information and communications technologies (ICTs) makes cyber-physical systems vulnerable to targeted attacks that are deceptive, persistent, adaptive and…

One of the widely used cyber deception techniques is decoying, where defenders create fictitious machines (i.e., honeypots) to lure attackers. Honeypots are deployed to entice attackers, but their effectiveness depends on their…

Popular methods in cooperative Multi-Agent Reinforcement Learning with partially observable environments typically allow agents to act independently during execution, which may limit the coordinated effect of the trained policies. However,…

Gamification applies game mechanics to non-game environments to motivate and engage users. Artificial Intelligence (AI) offers powerful tools for personalizing and optimizing gamification, adapting to users' needs, preferences, and…

Automated content filtering and moderation is an important tool that allows online platforms to build striving user communities that facilitate cooperation and prevent abuse. Unfortunately, resourceful actors try to bypass automated filters…

Recent research on vulnerabilities of deep reinforcement learning (RL) has shown that adversarial policies adopted by an adversary agent can influence a target RL agent (victim agent) to perform poorly in a multi-agent environment. In…

This paper proposes an active attack detection scheme for constrained cyber-physical systems. Despite passive approaches where the detection is based on the analysis of the input-output data, active approaches interact with the system by…

Language Model (LM)-based agents remain largely untested in mixed-motive settings where agents must leverage short-term cooperation for long-term competitive goals (e.g., multi-party politics). We introduce Cooperate to Compete (C2C), a…