SURL AI News
繁中English日本語

Archive

AI 安全

模型安全、資安、隱私、供應鏈、紅隊與防護。

AI 安全

Claude’s Automated Post-Training Mitigates Ten Classes of Alignment Failure, but Known Evaluations May Still Be Optimized Against

Anthropic’s automated alignment research agent can independently review the literature, design data, and post-train models, closing 26% to 96% of the evaluation gap across ten safety problems. It also outperformed a constrained baseline of human proposals, though the agent received more time to iterate, and the results demonstrate only its ability to remediate measurable failures.
AI 安全

Official llms.txt Files Led Coding Agents to Install Unclaimed Packages, Turning the Documentation Supply Chain Into an Execution Boundary

Pandex found hundreds of installation commands in enterprise AI-facing documentation that referenced unregistered packages or domains. Claude, Codex, and Hermes subsequently executed beacons planted by researchers in real enterprise environments. The issue is not the llms.txt format itself, but agents promoting trusted documentation directly into executable commands while bypassing package ownership and provenance verification.
AI 安全

Google Tests Double-Blind Model Evaluation in an H100 Secure Enclave, Keeping Model Weights and Confidential Test Sets Hidden from Each Other

Google DeepMind, MLCommons, and other organizations placed Gemini 2.5 Flash Lite and an undisclosed safety test set inside the same attestable secure enclave, with each party receiving only restricted results. The design reduces the risk of benchmark contamination, but trust still rests on hardware root keys, the trusted computing base, and cross-organizational code review.
最新模型

GLM-5.3 Releases 744B MoE Weights, but Million-Token Deployment Still Requires Data-Center-Class Resources

Two weeks after launching the API, Z.ai has released the GLM-5.3 weights. The model retains GLM-5.2’s base architecture, with capability gains driven primarily by post-training for agentic coding and cybersecurity. The FP8 files still total about 756GB, and the custom license and vendor-led evaluations mean that performance, safety, and legal validation remain necessary before adoption.
AI 安全

Fake Professional Dashboards Make LLM Agents More Willing to Bet, Raising the Action-Commitment Rate Across 12 Models to 36.8%

A new study finds that pairing inherently unpredictable questions with authoritative-looking data dashboards makes LLM agents more likely to make directional decisions—even when every figure is fabricated. Fine-tuning on 540 synthetic examples can temporarily repair the action gate, but enforcing a rigid output format causes the improvement to disappear.
AI 安全

D2C-Routing Separates AI Text Detection into Content and Expression Sources, Achieving 0.8603 TPR in Four-Class Classification at a Low False-Positive Rate

A Beihang University team no longer asks only whether text was generated by AI, but separately identifies the sources of its content development and surface expression. The system outperforms a rerun of RACE on the same data split in the reconstructed MixD2C test set, though cross-dataset generalization and full reproducibility remain limited.
AI 安全

LoopHarness Preserves Risk State Across Iterations, Reducing Overall ASR Across Five Agent Attack Classes to 0.1%

New research finds that guardrails reset after each trajectory cannot detect attack evidence distributed across multiple iterations, while simply decaying risk scores over time can be bypassed by waiting. Across 1,000 attacker-controlled episodes, LoopHarness preserved a 96.9% clean-task completion rate, though the results still require independent reproduction and validation in real-world systems.