i

i on Hugging Face Daily Papers: 21 papers, 1 in the top 3 of their day, 214 upvotes.

  1. Soft Instruction De-escalation Defense 3 upvotes, #20 of 2025-10-27
  2. Extracting alignment data in open models 6 upvotes, #23 of 2025-10-22
  3. SynthID-Image: Image watermarking at internet scale 1 upvotes, #38 of 2025-10-15
  4. The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections 8 upvotes, #32 of 2025-10-14
  5. Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated 1 upvotes, #25 of 2025-09-12
  6. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities 53 upvotes, #5 of 2025-07-14
  7. Cascading Adversarial Bias from Injection to Distillation in Language Models 6 upvotes, #32 of 2025-06-03
  8. Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models 7 upvotes, #42 of 2025-05-27
  9. Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation 3 upvotes, #54 of 2025-05-27
  10. Lessons from Defending Gemini Against Indirect Prompt Injections 8 upvotes, #26 of 2025-05-21
  11. Fixing 7,400 Bugs for 1$: Cheap Crash-Site Program Repair 6 upvotes, #32 of 2025-05-21
  12. Defeating Prompt Injections by Design 18 upvotes, #9 of 2025-03-25
  13. Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography 6 upvotes, #9 of 2025-01-16
  14. Hardware and Software Platform Inference 3 upvotes, #8 of 2024-11-13
  15. Stealing User Prompts from Mixture of Experts 13 upvotes, #7 of 2024-10-31
  16. Measuring memorization through probabilistic discoverable extraction 4 upvotes, #15 of 2024-10-30
  17. Operationalizing Contextual Integrity in Privacy-Conscious Assistants 3 upvotes, #14 of 2024-08-06
  18. A False Sense of Safety: Unsafe Information Leakage in 'Safe' AI Responses 7 upvotes, #8 of 2024-07-04
  19. UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI 5 upvotes, #22 of 2024-07-02
  20. Measuring memorization in RLHF for code completion 5 upvotes, #7 of 2024-06-20
  21. Model Dementia: Generated Data Makes Models Forget 7 upvotes, #3 of 2023-05-30

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.