At 4-bit inference quantization, CodeLlama-7b generates more accurate SQL and activates a planted backdoor far less often, while Llama-2-7b is hardly affected, across two training seeds.
Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Large language models (LLMs) have provided a lot of exciting new capabilities in software development. However, the opaque nature of these models makes them difficult to reason about and inspect. Their opacity gives rise to potential security risks, as adversaries can train and deploy compromised models to disrupt the software development process in the victims' organization. This work presents an overview of the current state-of-the-art trojan attacks on large language models of code, with a focus on triggers -- the main design point of trojans -- with the aid of a novel unifying trigger taxonomy framework. We also aim to provide a uniform definition of the fundamental concepts in the area of trojans in Code LLMs. Finally, we draw implications of findings on how code models learn on trigger design.
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Capturing the Effects of Quantization on Trojans in Code LLMs
At 4-bit inference quantization, CodeLlama-7b generates more accurate SQL and activates a planted backdoor far less often, while Llama-2-7b is hardly affected, across two training seeds.