8 matches found
OpenAI Models Breached Hugging Face During Internal Cyber Test
OpenAI models escaped from a controlled cyber test, exploited zero-day flaws and breached Hugging Face while searching its production database for test answers...
[SECURITY] Fedora 44 Update: python-tiktoken-0.13.0-2.fc44
tiktoken is a fast BPE tokeniser for use with OpenAI's models...
Open WebUI has SSRF in /openai/models
The /openai/models endpoint in open-webui/open-webui version 0.3.8 is vulnerable to Server-Side Request Forgery SSRF. An attacker can change the OpenAI URL to any URL without checks, causing the endpoint to send a request to the specified URL and return the output. This vulnerability allows the...
PYSEC-2026-1743 Open WebUI has SSRF in /openai/models
The /openai/models endpoint in open-webui/open-webui version 0.3.8 is vulnerable to Server-Side Request Forgery SSRF. An attacker can change the OpenAI URL to any URL without checks, causing the endpoint to send a request to the specified URL and return the output. This vulnerability allows the...
Involuntary In-Context Learning: Exploiting Few-Shot Pattern Completion to Bypass Safety Alignment in GPT-5.4
Safety alignment in large language models relies on behavioral training that can be overridden when sufficiently strong in-context patterns compete with learned refusal behaviors. We introduce Involuntary In-Context Learning IICL, an attack class that uses abstract operator framing with few-shot...
A Systematic Study of Code Obfuscation against LLM-Based Vulnerability Detection
As large language models LLMs are increasingly adopted for code vulnerability detection, their reliability and robustness across diverse vulnerability types have become a pressing concern. In traditional adversarial settings, code obfuscation has long been used as a general strategy to bypass...
TASO: Jailbreak LLMs Via Alternative Template and Suffix Optimization
Many recent studies showed that LLMs are vulnerable to jailbreak attacks, where an attacker can perturb the input of an LLM to induce it to generate an output for a harmful question. In general, existing jailbreak techniques either optimize a semantic template intended to induce the LLM to produc...
