StepGuard
PulseAugur coverage of StepGuard — every cluster mentioning StepGuard across labs, papers, and developer communities, ranked by signal.
- 2026-08-26 product_launch Shanghai AI Lab announced StepGuard, a system to block AI agent attacks. source
-
Shanghai AI Lab's StepGuard blocks 77% of AI agent attacks
Shanghai AI Lab has developed StepGuard, a system designed to prevent malicious AI agent actions. StepGuard analyzes AI agent tool calls before they are executed, successfully blocking 77% of attacks while only slightly…
-
StepGuard system enhances AI agent safety with step-level control
Researchers have developed StepGuard, a novel system designed to monitor and control the actions of AI agents at a step-by-step level, rather than just evaluating completed trajectories. This approach aims to prevent se…
-
New frameworks LongGuard and StepGuard enhance LLM safety guardrails
Researchers have developed two new frameworks, LongGuard and StepGuard, to address safety failures in large language models (LLMs). LongGuard focuses on analyzing and mitigating failures in long-context guardrails, prop…
-
StepGuard framework enhances AI web navigation accuracy
Researchers have developed StepGuard, a new framework designed to improve the accuracy of AI agents performing web navigation tasks. The system addresses single-step fragility by employing Dynamic Dual-Policy Optimizati…