Author

Asif Pinjari

h-index 1 View on Semantic Scholar

We have 2 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents

DriftNet is presented, a dual-head trajectory Transformer that reads a logged tool-call trajectory and answers all three questions in one forward pass: one head classifies the trajectory as compromised or not, and a second assigns every step one of four labels (benign, injection point, hijacked, failed injection).

Asif Pinjari, Mithun Paul Saint-Germain · 0 citations

#artificial intelligence Preprint Sep 2026

AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories

AgentDrift is presented, a benchmark of 12,536 synthetic tool-call trajectories over five agent domains in which every one of the 71,024 steps carries one of four labels: benign, injection point, hijacked, or failed injection; it is shown that the LLM judge was itself fooled by the hard negatives.

Asif Pinjari, Mithun Paul Saint-Germain · 2 citations