Patrik Mada
Member of Technical Staff, Aisle
Prague, Czechia
Actions
Patrik studied medicine and worked in neuroscience research. He later moved into cybersecurity, joining Microsoft, where he worked on the Assume Breach program. For nearly two years, he has been an AI researcher at Aisle, focusing on methods for detecting Trojaned and backdoored machine-learning models. His work sits at the intersection of neuroscience, cybersecurity, and AI safety, with a particular interest in understanding and identifying hidden or adversarial model behavior.
Links
Hidden Triggers, Harmful Payloads: Auditing Trojan Open-Weight LLMs
Open-weight models are increasingly important. Guardrails on frontier models affect cybersecurity research are pushing us toward open-weight LLMs. But are you sure the quant you downloaded is safe?
Trojan models remain largely theoretical because they are difficult to identify. Triggers may be a date, codebase, environment, or pattern; malicious behaviour may include injecting vulnerable code, overlooking vulnerabilities, or favouring a dependency. An unknown trigger and payload create a challenging problem.
Most supervised fine-tuning methods for creating Trojans miss triggers, break normal tasks, or leak payloads without a trigger. We developed a robust pipeline for realistic Trojan models with specific, effective triggers that preserve standard capabilities.
Using a zoo of Trojan models, we test methods from linear probes to J-space across triggers, payloads, model sizes, and architectures. Our results provide a foundation for detecting and mitigating Trojans in open-weight LLMs.
[un]prompted - The AI Security Practitioner Conference Sessionize Event
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top