CAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents

Personalized language agents use persistent memory to adapt to users over time, but the same mechanism creates an attack surface. When new information conflicts with stored preferences, an agent must distinguish genuine preference drift from temporary context shifts, ambiguity, or adversarial...

ADAPTD: Adaptive Detection and Proactive Threat Defense for Autonomous APT Attacks

Advanced persistent threat APT actors increasingly employ sophisticated techniques to propagate laterally through segmented enterprise networks. Timely detection and defense depend on cross-subnetwork coordination, yet maintaining global situational awareness generates substantial communication...

Safety-Contract Graph Multi-Agent Reinforcement Learning for Autonomous Network Security Response

Autonomous network-security response systems promise to reduce Security Operations Centre SOC reaction latency, but reward-only multi-agent reinforcement learning MARL can improve security reward while remaining non-deployable. We present a safety-contract graph MARL framework and instantiate it ...

Belief in False Information: A Human-Centered Security Risk in Sociotechnical Systems

This paper provides a comprehensive literature review on the belief in false information, including misinformation, disinformation, and fake information. It addresses the increasing societal concern regarding false information, which is fueled by technological progress, especially advancements in...

A Descriptive Model for Modelling Attacker Decision-Making in Cyber-Deception

Cyber-deception is an increasingly important defensive strategy, shaping adversarial decision making through controlled misinformation, uncertainty, and misdirection. Although game-theoretic, Bayesian, Markov decision process, and reinforcement learning models offer insight into deceptive...

Adaptive Network Security Policies Via Belief Aggregation and Rollout

Evolving security vulnerabilities and shifting operational conditions require frequent updates to network security policies. These updates include adjustments to incident response procedures and modifications to access controls, among others. Reinforcement learning methods have been proposed for...

Improper Check For Unusual Or Exceptional Conditions

github.com/mattermost/mattermost-server is vulnerable to Improper Check For Unusual Or Exceptional Conditions. The vulnerability is caused due to a failure to restrict the input in POST /api/v4/users which allows a user to manipulate the creation date in POST /api/v4/users tricking the admin into...

Information Flows and Democracy

Henry Farrell and I published a paper on fixing American democracy: "Rechanneling Beliefs: How Information Flows Hinder or Help Democracy." Its much easier for democratic stability to break down than most people realize, but this doesnt mean we must despair over the future. Its possible, though...

Maximizing Onboarding: Giving managers the skills for success

Managing teams come with challenges as well as rewards. Managers drive individual and team performance, and the best managers drive employee connection and engagement. Akamai believes that employees are our biggest asset; by effectively and efficiently integrating them into the...