resk-logits
PulseAugur coverage of resk-logits — every cluster mentioning resk-logits across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
RESK Security releases open-source LLM security toolkits for TypeScript and Python
RESK Security has released two open-source libraries, resk-llm-ts for TypeScript and Resk-LLM for Python, designed to protect Large Language Model (LLM) applications from various security threats. These libraries functi…
-
New open-source tool blocks LLM jailbreaks at logit level
A new open-source tool called resk-logits has been released to enhance LLM safety by blocking harmful content at the logit level, before a token is sampled. This GPU-accelerated processor uses an Aho-Corasick algorithm …
-
New open-source tool filters LLM jailbreaks at the logits layer
Resk-Security has released resk-logits, an open-source Python library designed to prevent Large Language Model (LLM) jailbreaks by filtering at the logits layer. This approach intercepts potentially harmful tokens befor…
-
New tool resk-logits offers proactive LLM security at logit level
A new open-source tool called resk-logits offers a proactive approach to LLM security by intervening at the logit level, before tokens are sampled. Unlike traditional audits and guardrails that react to generated text, …
-
RESK Security launches logit-level LLM security tools
RESK Security has developed two new tools, resk-logits and reskSecure, designed to enhance LLM security by intervening at the logit level before tokens are sampled. These tools aim to prevent the generation of harmful c…
-
Model distillation attacks pose growing AI security threat
Model distillation attacks, where a smaller model learns from a larger one's outputs, pose an under-recognized security threat to AI systems. These attacks can bypass safety alignments, leading to models that generate h…
-
New open-source tool blocks LLM jailbreaks at GPU speed
A new open-source tool called resk-logits has been developed to enhance LLM safety by intercepting and suppressing harmful outputs at the logit level during token generation. This GPU-accelerated Aho-Corasick engine can…
-
Anthropic's Mythos 5 authorized, Fable 5 to return; OpenAI unveils GPT-5.6 series
The AI landscape has been significantly reshaped by recent developments, particularly concerning Anthropic's models and OpenAI's new releases. Anthropic's advanced cybersecurity model, Mythos 5, has received US governme…