Related papers: The Authorization-Execution Gap Is a Major Safety …
Agentic AI systems are deployed with expectations of substantial productivity gains, yet rigorous empirical evidence reveals systematic discrepancies between pre-deployment expectations and post-deployment outcomes. We review controlled…
Load balancing across a networked environment is a monotonous job. Moreover, if the job to be distributed is a constraint satisfying one, the distribution of load demands core intelligence. This paper proposes parallel processing through…
Agentic AI governance is a critical component of agentic AI infrastructure ensuring that agents follow their owner's communication and interaction policies, and providing protection against attacks from malicious agents. The…
Agentic AI is rapidly proliferating across diverse real-world domains such as software engineering, yet public trust has not kept pace. The central reason is that responsibility, despite being widely discussed, remains a subjective and…
There is an increasing need for automated support for humans monitoring the activity of distributed teams of cooperating agents, both human and machine. We characterize the domain-independent challenges posed by this problem, and describe…
Recent work has framed intelligence in verifiable tasks as reducing time-to-solution through learned structure and test-time search, while systems work has explored learned runtimes in which computation, memory and I/O migrate into model…
Recent events surrounding the relationship between frontier AI suppliers and national-security customers have made a structural problem newly visible: once a privately governed model becomes embedded in military workflows, the supplier can…
Reasoning over heterogeneous artifacts (PDFs, spreadsheets, slide decks, etc.) increasingly occurs within structured agent workflows that iteratively extract, transform, and reference external information. In these workflows, uncertainty is…
As autonomous AI agents increasingly populate the Internet, a novel security challenge arises: "Is this entity an AI agent?" It is a new entity-type verification problem with no established solution. We formalize the problem through a…
As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in artificial intelligence security. Existing defense architectures…
The problem of assigning agents to tasks is a central computational challenge in many multi-agent autonomous systems. However, in the real world, agents are not always perfect and may fail due to a number of reasons. A motivating…
When an autonomous agent behaves undesirably, including failure to complete a task, it can be difficult to determine whether the behavior is due to a systemic agent error, such as flaws in the model or policy, or an environment error, where…
AI agents capable of GUI understanding and Model Context Protocol are increasingly deployed to automate mobile tasks. However, their reliance on over-privileged, static permissions creates a critical vulnerability: instruction injection.…
Open-weight large language models (LLMs) unlock huge benefits in innovation, personalization, privacy, and democratization. However, their core advantage - modifiability - opens the door to systemic risks: bad actors can trivially subvert…
AI systems face a growing number of AI security threats that are increasingly exploited in the real world. Hence, shared AI incident reporting practices are emerging in industry as best practice and as mandated by regulatory requirements.…
This paper systematically investigates the security, privacy, and ethical risks, as well as the traceability challenges of OpenClaw, a locally executable AI agent system for natural language interaction and real-world task completion. While…
As researchers continue to optimize AI agents for more effective task execution within operating systems, they often overlook a critical security concern: the ability of these agents to detect "impostors" within their environment. Through…
As the industry increasingly adopts agentic AI systems, understanding their unique vulnerabilities becomes critical. Prior research suggests that security flaws at the model level do not fully capture the risks present in agentic…
Failure attribution in multi-agent systems -- pinpointing the exact step where a decisive error occurs -- is a critical yet unsolved challenge. Current methods treat this as a pattern recognition task over long conversation logs, leading to…
Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…