i

iliashum's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 8 days ago

Soft Instruction De-escalation Defense

Paper • 2510.21057 • Published 11 days ago • 3

upvoted a paper 13 days ago

Extracting alignment data in open models

Paper • 2510.18554 • Published 14 days ago • 7

upvoted a paper 20 days ago

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections

Paper • 2510.09023 • Published 25 days ago • 8

upvoted a paper 4 months ago

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Paper • 2507.06261 • Published Jul 7 • 63

upvoted a paper 5 months ago

Cascading Adversarial Bias from Injection to Distillation in Language Models

Paper • 2505.24842 • Published May 30 • 6

upvoted 2 papers 6 months ago

Lessons from Defending Gemini Against Indirect Prompt Injections

Paper • 2505.14534 • Published May 20 • 8

Fixing 7,400 Bugs for 1$: Cheap Crash-Site Program Repair

Paper • 2505.13103 • Published May 19 • 6

upvoted a paper about 1 year ago

Operationalizing Contextual Integrity in Privacy-Conscious Assistants

Paper • 2408.02373 • Published Aug 5, 2024 • 5