Related papers: Detecting Safety Violations Across Many Agent Trac…
The gaming industry has experienced substantial growth, but cheating in online games poses a significant threat to the integrity of the gaming experience. Cheating, particularly in first-person shooter (FPS) games, can lead to substantial…
Side-channel attacks exploit unintended information leakage from system behavior and continue to pose serious privacy risks in modern platforms. Despite extensive prior work, side-channel analysis remains largely manual and fragmented,…
Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…
In the current rapidly changing digital environment, businesses are under constant stress to ensure that their systems are secured. Security audits help to maintain a strong security posture by ensuring that policies are in place, controls…
The rise of large language model (LLM)-based multi-agent systems (MAS) introduces new security and reliability challenges. While these systems show great promise in decomposing and coordinating complex tasks, they also face multi-faceted…
Fine-tuned large language models can exhibit reward-hacking behavior arising from emergent misalignment, which is difficult to detect from final outputs alone. While prior work has studied reward hacking at the level of completed responses,…
As large language models become more prevalent, their possible harmful or inappropriate responses are a cause for concern. This paper introduces a unique dataset containing adversarial examples in the form of questions, which we call AttaQ,…
Multi-Agent Path Finding (MAPF) is an important core problem for many new and emerging industrial applications. Many works appear on this topic each year, and a large number of substantial advancements and performance improvements have been…
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…
Evaluating safety performance in a resource-efficient way is crucial for the development of autonomous systems. Simulation of parameterized scenarios is a popular testing strategy but parameter sweeps can be prohibitively expensive. To…
This work investigates the potential of undermining both fairness and detection performance in abusive language detection. In a dynamic and complex digital world, it is crucial to investigate the vulnerabilities of these detection models to…
We study the problem of developing autonomous agents that can follow human instructions to infer and perform a sequence of actions to complete the underlying task. Significant progress has been made in recent years, especially for tasks…
Multi-Agent Systems (MAS) are notoriously complex and hard to verify. In fact, it is not trivial to model a MAS, and even when a model is built, it is not always possible to verify, in a formal way, that it is actually behaving as we…
The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…
AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prompt injection. To address these…
Mobile apps often embed authentication secrets, such as API keys, tokens, and client IDs, to integrate with cloud services. However, developers often hardcode these credentials into Android apps, exposing them to extraction through reverse…
This paper identifies an intrusion surveillance framework which provides an analyst with the ability to investigate and monitor cyber-attacks in a covert manner. Where cyber-attacks are perpetrated for the purposes of espionage the ability…
Multiplayer online gaming has witnessed an explosion in popularity over the past two decades. However, security issues continue to give rise to in-game cheating, deterring honest gameplay, detracting from user experience, and ultimately…
Safety risks arise as large language model-based agents solve complex tasks with tools, multi-step plans, and inter-agent messages. However, deployer-written policies in natural language are ambiguous and context dependent, so they map…
Context: Static Application Security Testing Tools (SASTTs) identify software vulnerabilities to support the security and reliability of software applications. Interestingly, several studies have suggested that alternative solutions may be…