Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents

LLM-based agents extend large language models with long-term memory LTM that persists privacy-sensitive user data across sessions. Production systems mitigate extraction risks through memory isolation, binding each user's LTM to a unique identifier. This defense has blocked known attacks on share...

Enhanced Multi-Class DDoS Attack Identification Using a Meta-Learning Ensemble

Distributed Denial of Service DDoS attacks continue to pose significant threats to network availability and security. While many detection systems focus on binary classification attack vs. benign, effective mitigation often requires identifying the specific type of DDoS attack. This paper...

Missing validation causes denial of service via `LSTMBlockCell`

ImpactThe implementation of tf.rawops.LSTMBlockCell does not fully validate the input arguments. This results in a CHECK-failure which can be used to trigger a denial of service attack:pythonimport tensorflow as tftf.rawops.LSTMBlockCell x=tf.constant0.837607, shape=28,29, dtype=tf.float32,...

Hijacking Agent Memory: Stealthy Trojan Attacks through Conversational Interaction

Large language model LLM agents increasingly leverage long term memory to support persistent and autonomous task execution. However, this capability also introduces a new attack surface: memory poisoning, where adversaries can inject malicious information to influence future behavior. Existing...

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration

Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more realistic threat model than prior memory poisoning work:...

Spring AI Agentic Patterns (Part 6): AutoMemoryTools — Persistent Agent Memory Across Sessions

File-Based Long-Term Memory for Spring AI Agents Agents are only as useful as what they remember. Spring AI's Chat Memory stores the full conversation and can persist it across restarts, but when the window fills, the oldest messages are evicted. The upcoming Session API will add recursive...

Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents

Large language models LLMs have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to limited interaction, weak execution grounding, and a lack of experience reuse. We propose Co-RedTeam, a security-aware...

WBHT: a Generative Attention Architecture for Detecting Black Hole Anomalies in Backbone Networks

We propose the Wasserstein Black Hole Transformer WBHT framework for detecting black hole BH anomalies in communication networks. These anomalies cause packet loss without failure notifications, disrupting connectivity and leading to financial losses. WBHT combines generative modeling, sequential...

Friday Squid Blogging: Pet Squid Simulation

From Hackaday.com, this is a neural network simulation of a pet squid. Autonomous Behavior: The squid moves autonomously, making decisions based on his current state hunger, sleepiness, etc.. Implements a vision cone for food detection, simulating realistic foraging behavior. Neural network can...