A 114k compositional jailbreak dataset is created, generators are fine-tuned for on-the-fly synthesis, and OPTIMUS introduces a continuous evaluator that identifies stealth-optimal regimes missed by binary attack success rates.
Selfdefend: Llms can defend themselves against jailbreaking in a practical manner,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
fields
cs.CR 3verdicts
UNVERDICTED 3representative citing papers
The work introduces and partially evaluates seven cross-domain prompt injection detectors, reporting F1 gains on benchmarks like deepset/prompt-injections and indirect-injection sets via local alignment, stylometry, and fatigue tracking.
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
citing papers explorer
-
The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring
A 114k compositional jailbreak dataset is created, generators are fine-tuned for on-the-fly synthesis, and OPTIMUS introduces a continuous evaluator that identifies stealth-optimal regimes missed by binary attack success rates.
-
Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection
The work introduces and partially evaluates seven cross-domain prompt injection detectors, reporting F1 gains on benchmarks like deepset/prompt-injections and indirect-injection sets via local alignment, stylometry, and fatigue tracking.
-
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.