Harsh Chaudhari
Scholar

Harsh Chaudhari

Google Scholar ID: w1lHWJ4AAAAJ
Northeastern University
Machine Learning Security and Privacy
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
870
 
H-index
9
 
i10-index
9
 
Publications
19
 
Co-authors
20
list available
Publications
13 items
PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs
2026
Cited
0
Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models
2026
Cited
0
Identifying Models Behind Text-to-Image Leaderboards
2026
Cited
0
The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
2025
Cited
0
Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security
2025
Cited
0
Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated
2025
Cited
0
Exploiting Leaderboards for Large-Scale Distribution of Malicious Models
2025
Cited
0
Cascading Adversarial Bias from Injection to Distillation in Language Models
2025
Cited
0
Co-authors
12 total
Alina Oprea
Alina Oprea
Northeastern University
Matthew Jagielski
Matthew Jagielski
Anthropic
Milad Nasr
Milad Nasr
OpenAI
Rahul Rachuri
Rahul Rachuri
Visa Research
Christopher A. Choquette-Choo
Christopher A. Choquette-Choo
OpenAI
Giorgio Severi
Giorgio Severi
Microsoft
Jonathan Ullman
Jonathan Ullman
Associate Professor of Computer Science, Northeastern University
Ilia Shumailov
Ilia Shumailov
AI Sequrity Company