The paper demonstrates that an external observer can identify the type of workload running on an NVIDIA H200 GPU by analyzing its power draw, distinguishing training, inference, and non‑AI tasks with high accuracy. Using 930 recorded traces, the authors achieve 97% accuracy and a macro‑averaged F1 score of 0.955 on unseen model families. They also test four evasion strategies to disguise training as inference, showing that a hardened detector can catch most attacks, though one strategy (LoRA) remains partially detectable.
By Simone Gargiulo, Gabriel Kulp
arXiv:2607. 19321v1 Announce Type: new Abstract: As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be untrusted.
By Lena Libon, Ben Rank, Jehyeok Yeon, David Schmotz, Jeremy Qin, Daniel Donnelly, Derck Prinzhorn, Maksym Andriushchenko
arXiv:2610.07476v1 Announce Type: cross
Abstract: Frontier AI treaties or agreements on limiting computation require external verification; an external auditor must be able to confirm how much comput...
By Tom Kimpson, Mauricio Baker, Emlyn Graham
arXiv:2610.18948v1 Announce Type: cross
Abstract: Finite safety assessments cannot exclude an adversary that preserves unattacked behavior until certification and activates afterward. We characterize...
By Inderjeet Singh
arXiv:2609.36049v1 Announce Type: cross
Abstract: Worker-monitor setups are a promising approach to AI oversight, but training workers against fixed monitors can incentivize monitor evasion. We study...
By Joseph H. Rudoler, Kevin Tan, Benedict Tessler, Timothy Kong, Enric Boix Adser\`a
The paper introduces the Power Flexibility Index (PFI) to measure how large language model (LLM) training performance changes when GPU power is reduced. Using 131 training runs on H200 and H100 GPUs, the study finds that LLM jobs have significant but variable power elasticity and identifies telemetry signals that can predict PFI during runtime. The authors demonstrate that allocating power based on PFI maximizes overall token throughput, recovering about 1.5k tokens/s per job under a 30% power reduction, which represents 63% of the gap between equal-weight and perfect-information allocations.
By Philip Colangelo, Charles Dawson, Shayan Sengupta, Ayse Coskun, Varun Sivaram
arXiv:2607. 06643v1 Announce Type: cross Abstract: Backdoor attacks severely threaten large-scale AI models.
By Issam Seddik, Sami Souihi, Mohamed Tamaazousti, Sara Tucci Piergiovanni
OVIG is an optimistic verification framework that audits AI training by replaying the process and comparing gradient differences against an empirically calibrated boundary. It treats any gradient difference exceeding this boundary as a malicious deviation. By partitioning training into stride‑s intervals and storing evidence only at interval endpoints, OVIG dramatically reduces off‑chain storage and transmission costs while maintaining zero attack success rate across language, vision, and diffusion workloads.
By Hongxu Su, Jianzhu Yao, Huan Zhang, Xuechao Wang, Pramod Viswanath
LEASH is a training‑free framework that enables uncertainty‑aware escalation from a weak to a strong computer‑use agent. It uses latent uncertainty signals from the weak agent’s hidden states to decide when to hand off control, and a shadow observer to maintain oversight of the strong black‑box agent. Experiments on OSWorld show LEASH improves task success over standalone weak agents and outperforms random escalation, achieving comparable performance to Claude Opus 5 while cutting inference cost by 19.2%.
By Qingni Wang, Changdae Oh, Yuzhe Yang, Sharon Li, Jiachen Yang, Ang Li, Xin Eric Wang
arXiv:2607. 07368v1 Announce Type: cross Abstract: AI control is a family of techniques to prevent an AI with malicious goals from subverting its operator's intent.
By Oliver Makins, Orazio Angelini, Zohreh Shams, Mary Phuong
arXiv:2610.27735v1 Announce Type: new
Abstract: Recursive self-improvement, in which frontier AI models work on training the next generation, is quickly becoming a reality. However, the safety of thi...
By Kaiwen Zhou, Udari Madhushani Sehwag
The paper presents an autonomous agent that designs machine learning algorithms for wireless power control, eliminating manual specification of architecture, loss, and training details. Using an autoresearch protocol, the agent iteratively edits a training script, runs experiments, and evaluates changes against a single metric, ultimately achieving 99.5% of a reference solution with vastly reduced inference cost. The agent’s discovered output parameterization matches the exact max‑min‑optimal allocation at the minimum percentile for all trained weights, demonstrating a principled, scalable approach to a complex, NP‑hard problem.
By Ahmad Khan, Akram Bin Sediq, Sara Azadegi Naeini, Raviraj S. Adve