LLMs for code vulnerability detection show average susceptibility of 33.2% to framing, 23.5% to anchoring, and 18.4% to halo effects, with a black-box attack suppressing up to 97% of detections.
Adver- sarial suffix filtering: a defense pipeline for llms
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLM cascade systems are vulnerable to a new adversarial attack that simultaneously degrades accuracy and destroys the intended cost savings by targeting both the lightweight models and the escalation decision mechanism.
citing papers explorer
-
Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection
LLMs for code vulnerability detection show average susceptibility of 33.2% to framing, 23.5% to anchoring, and 18.4% to halo effects, with a black-box attack suppressing up to 97% of detections.
-
When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack
LLM cascade systems are vulnerable to a new adversarial attack that simultaneously degrades accuracy and destroys the intended cost savings by targeting both the lightweight models and the escalation decision mechanism.