Papers

Filtered to model security · clear filter

Browse by term

continual learning 86reinforcement learning 48benchmarking 13large language models 12benchmarks 11vision-language models 10language models 9robotics 7world models 7natural language processing 6recursive self-improvement 6generative models 5on-policy distillation 5video generation 5attention mechanisms 4coding agents 4LLMs 4multi-agent systems 4multimodal learning 4multimodal models 4self-distillation 4self-supervised learning 4transformers 4vision-language-action models 4world modeling 4agent-based systems 3agentic models 3agentic search 3agents 3autonomous systems 3

Matching papers

Stealing Reasoning Traces from Proprietary LLM APIs

86 upvotes · 10 AUG 2026 · Alexander Panfilov, David Schmotz, Ilia Shumailov et al.

This paper reveals a vulnerability in how large language model providers store and return their models' step-by-step reasoning, allowing attackers to extract sensitive information and potentially inject malicious code. Practitioners should care because this vulnerability can be exploited to steal proprietary models' reasoning and private data, as well as inject malicious payloads into public models.

large language modelsencryptionvulnerability exploitationdata extractionmodel security