ENTITY
jailbreak prompts
jailbreak prompts
PulseAugur coverage of jailbreak prompts — every cluster mentioning jailbreak prompts across labs, papers, and developer communities, ranked by signal.
Total · 30d
1
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
0
1 over 90d
TIER MIX · 90D
TOPICS
RECENT · PAGE 1/1 · 2 TOTAL
-
Canary Method offers safe, objective LLM red-teaming
Two articles propose the "Canary Method" for red-teaming Large Language Model (LLM) applications, offering a safer and more objective approach than traditional jailbreak prompts. This method involves embedding meaningle…
-
New method re-triggers LLM safeguards to detect jailbreak prompts
Researchers have developed a novel method to enhance the detection of jailbreak prompts in large language models. This technique works by re-triggering the LLM's existing internal safeguards, which can be bypassed by so…