collaborators

16 papers

cs.CR2026

Backdoor Decontamination Dynamics in LLM Agents

Gabriel Huang, Abhay Puri, Léo Boisvert +4

Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing. Assuming defender…

cs.CL2026

PrivacyAlign: Contextual Privacy Alignment for LLM Agents

Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet +3

AI agents acting on behalf of users are constantly making decisions, and for users to trust their agents, those decisions must align with what they actually want. Privacy is an imp…

cs.CR2026

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

Léo Boisvert, Léo Boisvert, Abhay Puri +8

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.CR2026

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.GR2026

VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing

Juan Rodriguez, Haotian Zhang, Abhay Puri +13

We introduce VectorGym, a comprehensive benchmark suite for Scalable Vector Graphics (SVG) that spans generation from text and sketches, complex editing, and visual understanding.…

cs.LG2026

Scale Dependent Data Duplication

Joshua Kazdan, Noam Levi, Rylan Schaeffer +6

Data duplication during pretraining can degrade generalization and lead to memorization, motivating aggressive deduplication pipelines. However, at web scale, it is unclear what co…