Paper

"I Strongly Suspect This Website Is a Scam": Benchmarking PII Leakage and Detection without Defense in Autonomous Web Agents

Unreadunread

AI summary

arXiv:2606. 00497v1 Announce Type: new Abstract: Deceptive web content, widely instantiated across the internet and commonly known as \textit{social-engineering attacks}, manipulates autonomous web agents into submitting users' personally identifiable information (PII) to attacker-controlled endpoints.

Reading status

Priority

About this paper

Authors: Soham Roy, Sarthakbrata Halder, Arya Bharaty, Vaibhav Bhaskar, Yash Sinha, Dhruv Kumar, Srikant Panda, Murari Mandal
Released: 2026-06-02 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because "I Strongly Suspect This Website Is a Scam": Benchmarking PII Leakage and Detection without Defense in Autonomous Web Agents overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: strong, text, fill, persona, latin, under, wrong, line. Source: arxiv cs.CR (Cryptography and Security).
arXiv: 2606.00497

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to "I Strongly Suspect This Website Is a Scam": Benchmarking PII Leakage and Detection without Defense in Autonomous Web Agents. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.