Impact
Security research involving user or training data privacy
114 matching entries
Exposed retrieval embeddings can reveal source text. SHAQ evaluates indexing generated queries instead of direct document embeddings to reduce that leakage.
Untrusted document images can redirect vision-language agents across instruction and tool-authorization boundaries. Repeat-After-Me evaluates six victim models on constructed document tasks.
Deleting a memory record can leave its information in an agent's summaries, pending plans and KV cache. The paper evaluates revocation across this derived execution state.
Document-image PII detection can miss identifiers despite improving average localization scores. LeakageBench evaluates 500 pages with 11,954 annotations.
A compromised serving framework can violate user-data isolation through shared GPU state. GIFT evaluates per-user information-flow enforcement in vLLM and DistServe.
API gateways can pool distinct customers into one upstream cache identity. The authors observe cross-customer cache reuse in five deliberately pooled gateway configurations through two provider interfaces.
The authors report historical isolation failures in client-held encrypted reasoning blocks across compatible provider API contexts.
AgentS4D measures unsafe actions and state changes across complete workspace-agent executions rather than treating task completion or isolated model responses as safety evidence. Its 328 sandboxed cases introduce risky content through user requests, documents, web resources, tools, third-party skills, and persistent memory, then compare the same cases across four agent harnesses and five model backends.
OpenSkillRisk evaluates whether agent harnesses safely handle third-party skills that introduce risky behavior through otherwise plausible, benign tasks. The benchmark assembles 263 risky skills from public agent-skill ecosystems and tests three CLI-agent harnesses against seven risk categories using isolated task workspaces, mocked external services, and execution-level evidence.
HANDBOOK.md measures whether an agent can apply detailed organizational rules while completing realistic, multi-step enterprise tasks. The vendor-authored benchmark includes 65 resettable MCP-backed workflows, policy documents of 20 to 124 pages, and 824 deterministic rubric checks covering required decisions, prohibited actions, and final environment state.