11 3

i

iliashum

AI & ML interests

None yet

Recent Activity

authored a paper 4 days ago

Lessons from Defending Gemini Against Indirect Prompt Injections

authored a paper 4 days ago

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

upvoted a paper 4 days ago

Lessons from Defending Gemini Against Indirect Prompt Injections

View all activity

Organizations

None yet

iliashum's activity

authored 2 papers 4 days ago

Lessons from Defending Gemini Against Indirect Prompt Injections

Paper • 2505.14534 • Published 4 days ago • 8

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

Paper • 2505.13103 • Published 5 days ago • 6

upvoted 2 papers 4 days ago

Lessons from Defending Gemini Against Indirect Prompt Injections

Paper • 2505.14534 • Published 4 days ago • 8

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

Paper • 2505.13103 • Published 5 days ago • 6

commented 2 papers 4 days ago

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

Paper • 2505.13103 • Published 5 days ago • 6 •

Lessons from Defending Gemini Against Indirect Prompt Injections

Paper • 2505.14534 • Published 4 days ago • 8 •

commented a paper 6 days ago

Humans expect rationality and cooperation from LLM opponents in strategic games

Paper • 2505.11011 • Published 9 days ago • 4 •

authored a paper 2 months ago

Defeating Prompt Injections by Design

Paper • 2503.18813 • Published Mar 24 • 20

commented a paper 2 months ago

Defeating Prompt Injections by Design

Paper • 2503.18813 • Published Mar 24 • 20 •

commented a paper 4 months ago

Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography

Paper • 2501.08970 • Published Jan 15 • 6 •

authored a paper 6 months ago

Hardware and Software Platform Inference

Paper • 2411.05197 • Published Nov 7, 2024 • 4

commented a paper 6 months ago

Hardware and Software Platform Inference

Paper • 2411.05197 • Published Nov 7, 2024 • 4 •

commented 2 papers 7 months ago

Stealing User Prompts from Mixture of Experts

Paper • 2410.22884 • Published Oct 30, 2024 • 14 •

Measuring memorization through probabilistic discoverable extraction

Paper • 2410.19482 • Published Oct 25, 2024 • 4 •

upvoted a paper 10 months ago

Operationalizing Contextual Integrity in Privacy-Conscious Assistants

Paper • 2408.02373 • Published Aug 5, 2024 • 5

commented a paper 10 months ago

Operationalizing Contextual Integrity in Privacy-Conscious Assistants

Paper • 2408.02373 • Published Aug 5, 2024 • 5 •

commented 2 papers 11 months ago

A False Sense of Safety: Unsafe Information Leakage in 'Safe' AI Responses

Paper • 2407.02551 • Published Jul 2, 2024 • 9 •

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI

Paper • 2407.00106 • Published Jun 27, 2024 • 6 •

authored a paper almost 2 years ago

Model Dementia: Generated Data Makes Models Forget

Paper • 2305.17493 • Published May 27, 2023 • 5