conftrace_

adversarial prompt attack

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

prompt-based attack (1) reasoning alignment (1) decision criteria injection (1) heuristic shortcut (1) goal hijacking (1) attack success rate (1) prompt injection (1) security evaluation (1) reasoning model (1) adversarial attack (1)

Papers

Reasoning Hijacking: The Fragility of Reasoning Alignment in Large Language Models ACL 2026 Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models ACL 2025