PwS poisons CLLMs via a two-step training process so that code-style triggers cause vulnerable outputs while normal performance on benchmarks remains largely intact.
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CR 3verdicts
UNVERDICTED 3representative citing papers
SCOUT uses token saliency analysis to detect both standard and contextually-plausible backdoor attacks in language models while maintaining clean accuracy.
ACE decouples planning into abstract and concrete phases with static information-flow verification and enforces execution barriers to secure LLM app systems against prompt injection and related attacks.
citing papers explorer
-
Poison with Style: A Practical Poisoning Attack on Code Large Language Models
PwS poisons CLLMs via a two-step training process so that code-style triggers cause vulnerable outputs while normal performance on benchmarks remains largely intact.
-
SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
SCOUT uses token saliency analysis to detect both standard and contextually-plausible backdoor attacks in language models while maintaining clean accuracy.
-
ACE: A Security Architecture for LLM-Integrated App Systems
ACE decouples planning into abstract and concrete phases with static information-flow verification and enforces execution barriers to secure LLM app systems against prompt injection and related attacks.