Adversarial Multiplicity: Cherry-Picked Models and the Limits of Disclosure
cs.LG, stat.AP
Submitted: 2026-11-05
Updated: 2026-11-05
Sources
- Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits
- Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity
- Robust ML Auditing using Prior Knowledge
- Validity in machine learning for extreme event attribution
- Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases
- TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
- ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D
- Spline-Based Probability Calibration
- ZKBoost: Zero-Knowledge Verifiable Training for XGBoost
- X Hacking: The Threat of Misguided AutoML
- Trustless Audits without Revealing Data or Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis