activity
20232026
most citedLitLLMs, LLMs for Literature Review: Are we there yet?

5 citations · 8 across the 14 of their papers we have counts for

collaborators
Showing 2025Show all

7 papers · 1 filter

cs.CR2025

Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?

Rishika Bhagwatkar, Kevin Kasa, Abhay Puri +5

AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause unintended or harmful behavior. Inspi…

cs.CR2025

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain

Léo Boisvert, Abhay Puri, Chandra Kiran Reddy Evuru +7

While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the a…

cs.CL2025

BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning

Ahmed Masry, Abhay Puri, Masoud Hashemi +13

Charts are essential to data analysis, transforming raw data into clear visual representations that support human decision-making. Although current vision-language models (VLMs) ha…

cs.CV2025

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

Juan A. Rodriguez, Haotian Zhang, Abhay Puri +12

Scalable Vector Graphics (SVG) offer a powerful format for representing visual designs as interpretable code. Recent advances in vision-language models (VLMs) have enabled high-qua…

cs.CR2025

DoomArena: A framework for Testing AI Agents Against Evolving Security Threats

Leo Boisvert, Mihir Bansal, Chandra Kiran Reddy Evuru +9

We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1) It is a plug-in framework and integrates easily into realistic ag…

cs.CR2025

No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms

Joshua Kazdan, Abhay Puri, Rylan Schaeffer +5

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to…