Across 510 HarmBench behaviors and seven attack methods, GPT-4 models show more consistent jailbreak resilience than DeepSeek models, whose vulnerability grows with scale.
A survey of backdoor attacks and defenses on large language models: Implications for security measures.Authorea Preprints2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models
Across 510 HarmBench behaviors and seven attack methods, GPT-4 models show more consistent jailbreak resilience than DeepSeek models, whose vulnerability grows with scale.