DiffCodeGen clusters code candidates by behavioral similarity from fuzzing-synthesized inputs and selects the largest cluster's medoid, matching or exceeding prior test-time scaling methods with far less token and time cost.
In: Proceedings of the ACM SIGSAC Conference on Computer and Communications Security, New York, NY, USA, pp
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5roles
background 2polarities
background 2representative citing papers
RADAGAS-GPT4o achieves a 22.73% bypass rate against 10 WAFs, succeeding more against AI/ML-based firewalls than rule-based ones.
ContentFuzz rewrites posts with LLM guidance from stance model confidence to flip machine labels without altering human intent, tested across four models and three datasets in two languages.
A benchmarking experiment finds low rediscovery rates for three models on six Mythos-linked bug tasks, with only six target matches across 54 attempts under controlled prompting.
citing papers explorer
-
Code Generation by Differential Test Time Scaling
DiffCodeGen clusters code candidates by behavioral similarity from fuzzing-synthesized inputs and selects the largest cluster's medoid, matching or exceeding prior test-time scaling methods with far less token and time cost.
-
Adversarial SQL Injection Generation with LLM-Based Architectures
RADAGAS-GPT4o achieves a 22.73% bypass rate against 10 WAFs, succeeding more against AI/ML-based firewalls than rule-based ones.
-
Content Fuzzing for Escaping Information Cocoons on Digital Social Media
ContentFuzz rewrites posts with LLM guidance from stance model confidence to flip machine labels without altering human intent, tested across four models and three datasets in two languages.
-
Benchmarking Mythos-Linked Bug Rediscovery
A benchmarking experiment finds low rediscovery rates for three models on six Mythos-linked bug tasks, with only six target matches across 54 attempts under controlled prompting.
- Formal Verification of Probing Security via Conditional Independence