llm-engineering-prompts/upstream/trailofbits-awesome-ml-security/catalogue/impossibility_research.md

title, task, lineage_type, upstream_source, upstream_sha, imported_at, prompt_class, upstream_changes, author, validated

title	task	lineage_type	upstream_source	upstream_sha	imported_at	prompt_class	upstream_changes	author	validated
List of Papers		import	https://github.com/trailofbits/awesome-ml-security/blob/d7fe4fa9/impossibility_research.md	d7fe4fa9	2026-06-26	catalogue	accepted	upstream	false

List of Papers

• You can’t solve AI security problems with more AI
• Adversaries Can Misuse Combinations of Safe Models
• On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning
• Data Poisoning Won't Save You From Facial Recognition
• On the Impossible Safety of Large AI Models
• Beyond Labeling Oracles: What does it mean to steal ML models?
• Text Embeddings Reveal (Almost) As Much As Text
• Planting Undetectable Backdoors in Machine Learning Models
• Motivating the Rules of the Game for Adversarial Example Research
• On Evaluating Adversarial Robustness
• LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?
• Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models
• When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
• Adversarial Examples Are Not Bugs, They Are Features
• On Adaptive Attacks to Adversarial Example Defenses
• Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations
• Data Authenticity, Consent, & Provenance for AI are all broken: what will it take to fix them?
• Proof-of-Learning is Currently More Broken Than You Think
• On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
• Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses
• UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI