Related papers: DynaTrust: Defending Multi-Agent Systems Against S…
Multi-agent systems (MAS) have demonstrated significant effectiveness in addressing complex problems through coordinated collaboration among heterogeneous agents. However, real-world environments and task specifications are inherently…
Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces…
The field of textual adversarial defenses has gained considerable attention in recent years due to the increasing vulnerability of natural language processing (NLP) models to adversarial attacks, which exploit subtle perturbations in input…
In this paper, we consider the resilient multi-dimensional consensus and distributed optimization problems of multi-agent systems (MASs) in the presence of both agent-based and denial-of-service (DoS) attacks. The considered agent-based…
With the rapid progress of large language models (LLMs), LLM-powered multi-agent systems (MAS) are drawing increasing interest across academia and industry. However, many current MAS frameworks struggle with reliability and scalability,…
In real-time strategy (RTS) game artificial intelligence research, various multi-agent deep reinforcement learning (MADRL) algorithms are widely and actively used nowadays. Most of the research is based on StarCraft II environment because…
The routing performance in Mobile Ad-hoc Networks (MANETs) relies on the co-operation of the individual nodes that constitute the network. The existence of misbehaving nodes may paralyze the routing operation in MANETs. To overcome this…
Transformer-based models, such as BERT and GPT, have been widely adopted in natural language processing (NLP) due to their exceptional performance. However, recent studies show their vulnerability to textual adversarial attacks where the…
Jailbreak attacks pose significant threats to large language models (LLMs), enabling attackers to bypass safeguards. However, existing reactive defense approaches struggle to keep up with the rapidly evolving multi-turn jailbreaks, where…
Cooperative information shared among a multi-agent system (MAS) can be useful to agents to efficiently fulfill their missions. Relying on wrong information, however, can have severe consequences. While classical approaches only consider…
The area of Machine Learning as a Service (MLaaS) is experiencing increased implementation due to recent advancements in the AI (Artificial Intelligence) industry. However, this spike has prompted concerns regarding AI defense mechanisms,…
Multi-Agent Reinforcement Learning (MARL) discovers policies that maximize reward but do not have safety guarantees during the learning and deployment phases. Although shielding with Linear Temporal Logic (LTL) is a promising formal method…
Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their \textbf{reliance on static, pre-collected data distributions}. In this paper, we…
The need for autonomous and adaptive defense mechanisms has become paramount in the rapidly evolving landscape of cyber threats. Multi-Agent Deep Reinforcement Learning (MADRL) presents a promising approach to enhancing the efficacy and…
Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet their dual-stream architecture opens an underexplored attack surface: an adversary who injects…
Ensuring the safety and reliability of large language models (LLMs) in clinical practice is critical to prevent patient harm. However, LLMs are advancing so rapidly that static benchmarks quickly become obsolete or prone to overfitting,…
Industry 4.0's highly networked Machine Tool Controllers (MTCs) are prime targets for replay attacks that use outdated sensor data to manipulate actuators. Dynamic watermarking can reveal such tampering, but current schemes assume…
Dynamic trust evaluation in large, rapidly evolving graphs demands models that capture changing relationships, express calibrated confidence, and resist adversarial manipulation. DGTEN (Deep Gaussian-Based Trust Evaluation Network)…
Advanced Persistent Threats (APTs) represent a growing menace to modern digital infrastructure. Unlike traditional cyberattacks, APTs are stealthy, adaptive, and long-lasting, often bypassing signature-based detection systems. This paper…
Advanced Persistent Threats (APTs) have recently emerged as a significant security challenge for a cyber-physical system due to their stealthy, dynamic and adaptive nature. Proactive dynamic defenses provide a strategic and holistic…