Bias Injection Attacks on RAG Databases and Sanitization Defenses

defenses on vector databases in retrieval-augmented generation (RAG) systems. Prior work on knowledge poisoning attacks primarily inject false or toxic content, which fact-checking or linguistic analysis easily detects

Poster: ClawdGo: Endogenous Security Awareness Training for Autonomous AI Agents

Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving

Robust Single-message Shuffle Differential Privacy Protocol for Accurate Distribution Estimation

with ordinal nature. In this paper, we study the distribution estimation under pure shuffle model, which is a prevalent shuffle-DP framework without strong security assumptions. We initially attempt

MemLineage: Lineage-Guided Enforcement for LLM Agent Memory

ancestor, while still allowing benign recall. We evaluate three defense cells against three memory-poisoning workloads on a deterministic mechanism-isolation harness; MemLineage is the only configuration in that harness

SpectralGuard: Detecting Memory Collapse Attacks in State Space Models

State Space Models (SSMs) such as Mamba achieve linear-time sequence processing through input-dependent recurrence, but this mechanism introduces a critical safety vulnerability. We show that the spectral radius

Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses

Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage information, and context. While this has improved the agent's functionality

Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agents

Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence

mcp-shell — Security Disabled by Default in Bare-Binary Deploy

Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense

mechanism. At inference, retrieved cells serve as grounding context for precise safety decisions. Across model-level safety on HarmBench and agent-level safety on AgentHarm, Membrane achieves the highest

Fight Poison with Poison: Enhancing Robustness in Few-shot Machine-Generated Text Detection with Adversarial Training

Machine-generated text (MGT) detection is critical for regulating online

Beyond Small Patches: Black-Box Detection and Purification of Diverse Backdoor Triggers

defenses often rely on model internals, training data, or clean validation samples, making them difficult to deploy when only black-box access to a trained model is available. We propose

CIS-BA: Continuous Interaction Space Based Backdoor Attack for Object Detection in the Real-World

Object detection models deployed in real-world applications such as autonomous driving face serious threats from backdoor attacks. Despite their practical effectiveness,existing methods are inherently limited in both capability

Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems

user query on OpenAI's embedding models), and achieves near-100% retrieval across 11 benchmarks and 8 embedding models (including both open-source models and proprietary services). Based on this

Privacy Preserving Machine Learning Workflow: from Anonymization to Personalized Differential Privacy Budgets in Federated Learning

called privacy preserving machine learning architectures, such as federated learning. While federated learning enables model training on decentralized data preventing their sharing and centralization, it still faces several challenges related

SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions

Retrieval-Augmented Generation (RAG) systems are increasingly evolving into agentic architectures where large language models autonomously coordinate multi-step reasoning, dynamic memory management, and iterative retrieval strategies. Despite rapid industrial

Adaptive Intrusion Detection System using Transformer-Based Neural Networks and Continual Learning Approach with Adversarial Investigation

fixed traffic snapshots decay silently after deployment as threat distributions shift. Fine-tuning models on new attacks triggers catastrophic forgetting, while retraining from scratch is computationally infeasible. Replay-based continual

The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements

Agentic large language model systems that autonomously invoke tools, maintain persistent memory, and execute multi-step plans are increasingly deployed in public-facing domains, including government services, healthcare triage

STELP: Secure Transpilation and Execution of LLM-Generated Programs

Rapid evolution of Large Language Models (LLMs) has achieved major advances in reasoning, planning, and function-calling capabilities. Multi-agentic collaborative frameworks using such LLMs place them at the center

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models

hijack. Each category captures a distinct pathway through which an adversary can manipulate a model's behavior. We evaluate these threats using 12 representative attack methods spanning text, image

SEAL: Towards Persistent Tool Poisoning Attack against LLM Agents via Prefix-Eliciting Trigger

rounds. To investigate whether tool poisoning remains a practical threat in such realistic settings, we propose SEAL, a two-stage method for persistent tool poisoning. Specifically, SEAL first performs Prefix