How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE

arXiv:2609.09793 · cs.CR, cs.AI, cs.CL, cs.LG · Submitted 2026-09-09 · Read on arXiv

cs.CR, cs.AI, cs.CL, cs.LG

Submitted: 2026-09-09

Updated: 2026-09-09

Comments: 20 pages, 14 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 2× in this paper · explained in 1 episode
• Ablation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Mixture-of-Experts (MoE) — 1× in this paper · explained in 7 episodes
• Mixture-of-Experts (MoE) Models — 1× in this paper · explained in 3 episodes

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs