AgentPhishing: A Benchmark of LLM Email Agents Under Adaptive Attack
Computer-use agents increasingly handle private information and act on users' behalf across desktop and web applications
#cs.AI
共收录 1652 条相关情报。
← 返回所有主题Auditing the Hand-Written Inputs of Learned Access Control
Learned access control is typically deployed behind two hand-built artefacts: a hard-deny set enforced by a small truste
SecLog-Bench: A Scalable Benchmark for Cybersecurity Log Reasoning with Scaffolded Evidence
Large language models (LLMs) have shown strong potential for cybersecurity, leading to growing interest in LLM-based aut
MIG-COW: Transferable Adversarial Attacks on Deepfake Detectors via Gradient Decomposition
Despite recent advances, deepfake detectors remain vulnerable to adversarial examples, particularly in diverse, real-wor
Can Loan Processors and Underwriters Spot AI-Edited Statements? An Empirical Study
AI-assisted editing can produce loan documents that preserve familiar issuer layouts while changing the applicant's iden
AgentTriage: Replayable Security Diagnosis Across Heterogeneous Agent Runtimes
When tool-use agents write files, execute code, or send data, their final responses do not explain the resulting securit
Scaling Laws for Safety Probes
Safety probes trained on a model's activations are a standard tool for monitoring language models in real time. Each tim
Bridging the Closed-World Gap: Interpretable Anomaly Detection via a Hybrid TSK-FCM Ensemble on the BETH Dataset
A fundamental paradox plagues the deployment of Machine Learning in cybersecurity: supervised models generalize poorly t
Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
Modern LLM agents can retrieve information from accessible documents, and then disclose a sensitive conclusion assembled
Automated screening of privacy risks in medical AI
Medical artificial intelligence (AI) models are often shared without their training data, assuming this protects the pat
MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning
With the rapid integration of Multi-modal Large Language Models (MLLMs) into real-world applications, Prompt Injection (
Beyond Binary Labels: Diagnostic Evaluation of LLM Safety with Prompt-Level Rubrics
Current LLM safety benchmarks predominantly rely on binary safe or unsafe labels, lacking explanatory depth and sufferin
Correlated Failures of AI Approval Monitors
Before an AI agent takes a consequential action, such as paying, messaging or changing code, several monitors check it.
AgentPolicyForge: From Executable Environments to Policy Benchmarks and Adaptive Guards
Customized agent deployments define policies over tools, resources, and execution conditions. Providing these policies i
PerMIT: Securing Persistent Memory for LLM Agents via Machine-Checked Integrity Theorems and Scalable Community Trust
Persistent memory is a largely undefended surface for injection and poisoning, and the same risk limits memory sharing a
Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning
Large language model (LLM) agents are increasingly deployed in multi-agent systems (MAS) to accomplish complex tasks. Pr
Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise
The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt inje
CALLIOPE: Private Insights into AI Use, Without Embeddings
We introduce CALLIOPE, a top-down framework for discovering topic hierarchies in large corpora of unstructured data (e.g
Proof-Carrying Contracts: Commitments AI Agents Cannot Break
AI agents increasingly act on behalf of people or other agents, purchasing services, exchanging information and delegati
A Digital Twin to Improve Cyber-Social Impact
The increasing complexity of Industrial Control Systems (ICS) and their integration with IT infrastructures has signific