Unverified50% confidenceFactExact time
The hidden Markov preference model proposed in the paper treats the attacker's active behavior modes as hidden states, defines the action regularities under each mode on a 'feasibility mask tree' whose nodes correspond to executable actions, and the mask dynamically blocks infeasible action branches according to the current state.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/6/2026
First Seen
Valid until: 2/4/2027
Sources
Related Entities
Related Claims
UnverifiedAction masking sets the probabilities of illegal actions to zero and renormalizes when the policy network outputs action probabilities, ensuring that the agent samples only from legal actions; it can significantly accelerate training but may introduce implicit preferences leading to path dependence.72% similarUnverifiedDefenses based on known patterns have an inherent lag against new attack variants dynamically generated by agents.70% similarUnverifiedWhen evolving from passive Agents to proactive Agents, one can start with the most easily implementable scheduling mechanism and then progressively introduce event-driven and condition-triggered approaches.69% similarUnverifiedRule-based static regex matching is inherently difficult to extend to semantically-level attack variants.69% similarUnverifiedAgents dynamically decide their next action based on context, and their behavior paths are generated only at runtime, breaking the traditional security model's assumption that the behavior of an executing entity can be enumerated.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1142270API
curl https://kongchang.com/api/v1/knowledge/claims/1142270MCP
get_claim(id=1142270)