The next Shocklab Seminar will be held in person on Wednesday, 22 April 2026, from 16:00 - 17:00. Please join us in the Mathematics building for two short talks as part of our series by the Cooperative AI Research Fellows. Qi Guo will present on "Inter-agent Influence Evaluation" and Omer Kamal Ali Ebead will present on "Embedded Adversarial Agents in Multi-Agent LLM Systems"
Virtual Meeting Link: https://bit.ly/shocklab-seminars
 

Title: Inter-agent Influence Evaluation
Speaker: Qi Guo
Abstract: Persuasion and deception pose distinct risks in multi-agent settings. In the context of misuse, an AI agent instructed to pursue a harmful goal could use persuasion, deception, and other forms of influence to recruit other AI agents—combining their capabilities and steering their actions toward the harmful goal. We propose an evaluation framework for empirically assessing four inter-agent influence capabilities: persuasion, deception, coercion, and jailbreaking. We evaluate models in dyadic environments using the Inspect platform, complete with realistic tool access and simulated operational consequences. The benchmark enables systematic comparison of influence capability across models and informs both deployment decisions and safety research priorities.
Bio: Qi is an AI Safety early career researcher, currenly doing the Cooperative AI Research Fellowship hosted by AI Safety South Africa in Cape Town. She is collaborating with Cooperative AI Foundation doing inter-agent influence evaluations.

Title: Embedded Adversarial Agents in Multi-Agent LLM Systems
Speaker: Omer Kamal Ali Ebead
Abstract: LLM agents now hold sensitive user data and interact autonomously at scale but what happens when one agent is adversarial from the start? Unlike external attacks (prompt injection, jailbreaking), an embedded adversary is a trusted participant that exploits cooperative dynamics to extract private information through social channels. We build a benchmark framework grounded in Contextual Integrity theory (Nissenbaum, 2004), operationalized as a 7-factor schema that controls when sharing is contextually appropriate. Our automated pipeline generates diverse multi-agent scenarios, runs them in Google DeepMind's Concordia framework, and scores agents on their ability to discriminate between task-relevant sharing and private data protection.
Bio: Omer is a researcher working at the intersection of multi-agent systems and AI safety. His work spans Multi-Agent Reinforcement Learning (MARL) and cooperative AI, investigating how agents learn, generalise, and interact in complex multi-agent settings. Through his Master’s at Stellenbosch University and ongoing research fellowships, he combines theoretical foundations in AI with hands-on implementation, bringing a background in Electrical Engineering and full-stack development to advance safe and robust AI systems.
 

Housekeeping: