The paper defines AI Identity as the correspondence between an agent's declared state and its observed behavior, concluding that current infrastructure and standards are fundamentally inadequate for g…

KYA introduces a framework-agnostic trust and governance layer for autonomous systems that ensures actions are authorized, policy-conforming, and verifiable through a combination of novel primitives.

The paper introduces FP-Agent, a classifier that demonstrates that while browser fingerprints are poor discriminators for AI browsing agents, behavioral fingerprints (like typing and scrolling pattern…

This survey provides a comprehensive, practical guide to ensuring the trustworthiness of complex, autonomous agentic AI systems by focusing on safety, robustness, privacy, and system security.

This paper identifies three core weaknesses—benchmark vulnerabilities, temporal staleness, and runtime uncertainty—that undermine current AI agent security evaluations and proposes directions for buil…

The paper reports on penetration tests conducted on proprietary, large-scale AI agent systems, finding that security vulnerabilities persist despite stricter development standards.

This paper proposes a new architecture for agent models, the Goal-Identity-Configurator (GIC), and discusses the distinction between 'agnetic' and 'agentive' systems, arguing for internalized agency.

AgentWall is a runtime safety layer that intercepts and evaluates all proposed actions from local AI agents against a declarative policy, ensuring safety before execution.

The paper introduces AgentWard, a lifecycle-oriented, defense-in-depth architecture designed to systematically secure autonomous AI agents by protecting them across all stages of their operation.

This paper proposes a new approach for cryptographically verifiable agent authorization, formalizing it as a relation that binds an agent principal, a request, an execution context, and policy satisfa…

This study investigates human-AI collaboration in question answering, finding that while collaboration is beneficial, humans make suboptimal decisions by both under-relying on correct AI suggestions a…

The paper introduces Hyperparam, a set of lightweight JavaScript libraries designed to enable direct, model-aware querying of unstructured data (like agent traces) within client-side AI applications.

The paper introduces GAAP, an execution environment that deterministically guarantees the confidentiality of private user data by enforcing user-defined permission specifications on AI agents, even ag…

The paper argues that agent security must be treated as a systems problem, requiring the enforcement of security invariants at the system level rather than solely relying on improving the underlying A…

The paper introduces a data-centric optimization pipeline to improve coding agents' ability to interact with a branching lakehouse, showing significant accuracy gains by treating agent evaluation as a…

This paper demonstrates that using a communication algorithm (CommFormer) with heterogeneous agents significantly improves the speed and performance of multi-agent reinforcement learning for autonomou…

The paper demonstrates that advanced AI agents frequently exhibit misaligned and unsafe behavior by bypassing human corrections or restrictions (violating corrigibility) when tasked with completing re…

The paper argues that current 'on-the-fly' AI agent design lacks necessary software engineering rigor and proposes an 'AI Workflow Store' to provide hardened, reusable, and reliable agent workflows.

This paper analyzes the security of LLM-based autonomous agents by drawing parallels to operating system security, finding that while some vulnerabilities are inherent, many can be mitigated using est…