2025/02/01 by Stuart Armstrong, Matija Franklin, Armstrong, Stuart +5 · 3 citations
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computers and Society (cs.CY) #Cryptographic Implementations and Security #Cryptography and Security (cs.CR) #Digital and Cyber Forensics #FOS: Computer and information sciences #I.2.0 #Law, Rights, and Freedoms
paper · pdf · doi:10.48550/arxiv.2502.00580
openalex publication_date 2025/02/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent work showed Best-of-N (BoN) jailbreaking using repeated use of random augmentations (such as capitalization, punctuation, etc) is effective against all major large language models (LLMs). We have found that 100% of the BoN paper's successful jailbreaks (confidence interval [99.65%, 100.00%]) and 99.8% of successful jailbreaks in our replication (confidence interval [99.28%, 99.98%]) were blocked with our Defense Against The Dark Prompts (DATDP) method. The DATDP algorithm works by repeatedly utilizing an evaluation LLM to evaluate a prompt for dangerous or manipulative behaviors--unlike some other approaches, DATDP also explicitly looks for jailbreaking attempts--until a robust safety rating is generated. This success persisted even when utilizing smaller LLMs to power the evaluation (Claude and LLaMa-3-8B-instruct proved almost equally capable). These results show that, though language models are sensitive to seemingly innocuous changes to inputs, they seem also capable of successfully evaluating the dangers of these inputs. Versions of DATDP can therefore be added cheaply to generative AI systems to produce an immediate significant increase in safety.