AI & ML
From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
arXiv cs.CR0 views
arXiv:2511.19218v3 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly power web-facing applications, including conversational assistants and content services, where open user interaction exposes them to diverse safety threats and adaptive attacks. In particular, jailbreak attackers repeatedly reformulate harmful requests to bypass safety alignment. Although existing studies have concentrated on defending dynamic jailbreaks, they often retain discovered attacks as flat samples and discard information about how those attacks were found. In this paper, we introduce MACE, an MCTS-guided adversarial co-evolution framework that turns search into policy-learning signals for both an attacker and a defender. Its search component, GS-MCTS, explores multi-step compositions of rewriting operators and associates discovered attacks with empirical success frequency and path depth. Its optimization component, AC-TGPO, uses these statistics for difficulty-aware group-relative credit assignment and constructs a temporally asymmetric curriculum from current interactions, pairings between the latest attacker and preceding defender, and attacks that survive a defense update. Thus, MACE connects search structure to both within-round policy optimization and cross-round memory, rather than using MCTS only to generate attacks or treating each round as a flat adversarial dataset. Removing difficulty-aware weighting, asymmetric samples, or persistent hard samples increases defense ASR-LR by 3.7 %, 6.0 %, and 5.0 %, respectively. Across evaluated models, the resulting attacker achieves the highest ASR-LR in all six model--dataset settings, while the defender reduces average ASR-LR from 11.9 % for the best baseline to 8.8 %.
Source:https://arxiv.org/abs/2511.19218PreviousPSM: Prompt Sensitivity Minimization via LLM-Guided Black-Box OptimizationNextTowards Reliable Local Security Agents: Verifiable Post-Training for Linux Privilege Escalation
Related posts
Fluent English is not evidence of ASL understanding: lessons from building a video translator
0dev.to

Audit Trails and Explainability for Agentic AI in Code Events
0dev.to
By 3 p.m. the daily high was already final on 78% of days. In Madrid, 32% (49 airports, one year)
0dev.to

This smell startup says its AI nose is as good as a human’s
0MIT Technology Review

Debugging Claude Fable 5.2 Code Art: Truncated SVG, Broken Canvas, Working Render
0dev.to
Hydra · Coeziune OM–IA — the complete DOI registry (2026-11-18): 76 published works
0dev.to OpenSource