Understanding the Hierarchical Structure and Functional Landscape of the Model Context Protocol Ecosystem

AI agents increasingly rely on tools exposed through the Model Context Protocol MCP to complete user tasks. Hundreds of thousands of MCP servers are listed across marketplaces, yet they are organized only by coarse, marketplace-specific server categories. This makes it difficult for agents and...

Characterizing Security Effects of OSS Vulnerabilities in Agent Systems

Software agents increasingly depend on open-source components when executing tools and interacting with external systems. Security flaws in these dependencies may therefore influence more than the software process in which they occur: their consequences can be carried through tool outputs, agent...

Performance Analysis of Multiparty GHZ-State Quantum Conference Key Agreement over Optical Fiber Channel

Quantum conference key agreement QCKA enables multiple spatially separated users to establish a common key with composable information-theoretic security by exploiting multipartite quantum correlations. Greenberger--Horne--Zeilinger GHZ states are a natural resource for this task, but their...

Can CaMeLs Talk? Securing Multi-Agent Systems against Indirect Prompt Injection Attacks

Indirect prompt injection attacks - malicious instructions embedded in content processed by large language models - remain a major obstacle to safely deploying tool-using agents. CaMeL Debenedetti et al., 2025 mitigates this threat for an individual agent by separating trusted control flow from...

The Poisoned Conversation: Privacy-Leaking Watermarks in Unified Multimodal Models

Multimodal models are increasingly shifting toward unified architectures that understand and generate text, images, and other modalities within a shared conversational context. This design enables fluid interaction across modalities, but it also changes the privacy threat model: Information...

Who Is Your Agent Serving? Provider-Side Indirect Prompt Injection in Proactive Agents

Proactive personal agents increasingly decide what to recommend, how to personalize advice, and what follow-up assistance to offer, creating a new user-decision attack surface for provider-side indirect prompt injection. We show that an external provider need not access private user context,...

Adaptive Code Revision Attacks on AI Pull Request Reviewers

Pull-request review protects software before new code reaches users, helping prevent vulnerabilities that could expose users to attacks. AI agents increasingly perform these reviews and explain which problems need fixing. However, for an attacker submitting vulnerable code, this feedback also...

AutoDP-LLM: Automating Data Pre-Processing for Intrusion Detection Systems Using Large Language Models

The increasing complexity and scale of modern cyber-attacks demand intelligent and computationally efficient Intrusion Detection Systems IDS. However, designing effective data pre-processing pipelines traditionally involves substantial trial-and-error effort and repeated evaluation of alternative...

JASPER: Special Session on Joint Reliability and Security Assessment of SPlit Computing for Edge Robustness

Split Computing SC enables efficient deployment of Deep Neural Networks DNNs by partitioning inference between edge devices and cloud servers. However, intermediate feature representations are simultaneously exposed to hardware faults and adversarial attacks, which are traditionally evaluated...

Xalgorix Autonomous AI Pentesting Agent 4.6.139

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

Trusted Hardware Acceleration for Malicious-Secure Function Secret Sharing

Function secret sharing FSS underlies two-party private inference and private information retrieval, with cost dominated by generating, moving and evaluating distributed point function DPF keys. A trusted GPU-integrated distributed function accelerator DFA removed key movement by generating and...

Reactivating Alignment: Defending LLMs from Jailbreaks Via Intention-Aware Input-Output Matching

Large language models LLMs remain vulnerable to jailbreak attacks that conceal harmful intent within complex adversarial prompts. Existing defenses primarily rely on input perturbation or harmful-output suppression, but they rarely model where malicious intent resides, resulting in brittle...

Attestable Audit: Property-Based Attestation for Proprietary Workloads without Artifact Disclosure

Trusted Execution Environments TEEs prove the integrity of code and data to a remote peer through remote attestation: the TEE issues an attestation report by signing, with a hardware-bound key, its configuration information, including measurements cryptographic digests of the code loaded inside i...

The Same Zero: Why Identical ASR Can Imply Different Guarantees in LLM-Agent Security

LLM-agent security has produced a dense landscape of defenses - prompt hardening, content filters, permission gates, sandboxes - yet no framework tells a deployer what a defense actually guarantees, or where that guarantee comes from. We apply Verification Autonomy Levels VAL - L0: LLM...

COPEX: Benchmarking LLM Robustness to Adversarial Context across Model Context Protocol Layers

Large language models increasingly mediate tool use in Model Context Protocol MCP systems, where adversarial influence may enter through user instructions, tool schemas, tool outputs, or protocol messages. Existing benchmarks often evaluate deployed agents, conflating model susceptibility with...

Static Bootstrap Placement for Encrypted Language Model Decoding

Language models increasingly serve prompts that carry private data, and secure inference under homomorphic encryption lets a client outsource the computation without revealing the prompt. Existing secure inference systems run a forward pass without consuming a token under encryption, and generati...

Forecasting Cybersecurity Incidents Using Geopolitical Data and Large Language Models

Predicting security incidents is a profound task critical for informing proactive defensive measures and cyber-insurance policies. Prior work tackling this problem mainly utilized structured, manually defined features based on network measurements e.g., protocol misconfigurations. Still, despite...

Post-Quantum Authentication Protocol for Internet of Medical Things

IoMT communication systems should provide origin authentication and ensure integrity protection for the messages produced by patients' devices for transmission to gateways and further processing by other hospital services. With regard to IoMT, this paper discusses tampering, impersonation, and...

Karma Pro 0.13

Karma Pro is an open source code review tool written in Swift that can assist code reviewers with a multitude of useful tools. Karma Pro is a macOS source-code security scanner AST base and Heuristics that statically analyses projects in multiple languages. It's backed by an ML classifier trained...

Quantum Machine Learning Protection of Military Quantum Key Distribution against Cryptographically Camouflaged Attacks

Quantum key distribution proves its protocol secure and says nothing about the hardware beneath it, so military and government operators fielding it for command-and-control keys monitor the channel for implementation attacks, and that monitoring has a blind spot. An adversary with a kleptographic...

NetScaler 73.30 HTTP Request Smuggling

NetScaler version 73.30 contains an HTTP/1.1 chunk-size accumulator overflow that can cause request parsing desynchronization and request smuggling...

Joern 4.0.646

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

Maestro 0.17.6

Maestro is a cross-platform desktop app for orchestrating your fleet of AI agents and projects. It's a high-velocity solution for hackers who are juggling multiple projects in parallel. Designed for power users who live on the keyboard and rarely touch the mouse. Collaborate with AI to create...

Scapy Packet Manipulation Tool 2.8.0

Scapy is a powerful interactive packet manipulation tool, packet generator, network scanner, network discovery tool, and packet sniffer. It provides classes to interactively create packets or sets of packets, manipulate them, send them over the wire, sniff other packets from the wire, match answe...

Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate

Text watermarking helps identify AI-generated content, but its effect on factual reliability remains underexplored. In this paper, we study watermarking hallucination: factual errors induced or amplified by watermarking even when the required evidence is present in the context and the unwatermark...

StegoMemory: Agentic Memory Acts As Covert Steganographic Channel

Is agentic memory robust against stealthy steganographic attacks? We carry out a large-scale red-teaming exercise to test whether agents can encode attacker-controlled strings in one session and recover them in another without triggering safety oversight. Following SHADE-Arena-style tasks, we emb...

Bounded Reasoning: Cognitive Hierarchy in Human-Versus-AI Cyber Defense

Human-agent evaluations often compress interaction into a single performance score, even when human and automated policies adapt differently over time. We study this in a sequential cyber-defense game on an attack graph, where a human or reinforcement-learning defender protects cloud assets again...

Indistinguishability Lifting for Keyed Oracles, Compressed Ideal Cipher, and More Applications

Cryptographic security proofs often involve an adversary interacting with a larger, keyed oracle that consists of potentially exponentially many independent instances of a smaller, base oracle. However, showing quantum indistinguishability between two such keyed oracles can be tricky, since a...

From TS-SUF-2 to TS-SUF-4: Practical Security Enhancements for FROST2 Threshold Signatures

Threshold signature schemes play a vital role in securing digital assets within blockchain and distributed systems. FROST2 stands out as a practical threshold Schnorr signature scheme, noted for its efficiency and compatibility with standard verification processes. However, under the one-more...

Xalgorix Autonomous AI Pentesting Agent 4.6.136

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents

Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources. Existing benchmarks leave gaps in executable coverage of their runtime security risks, while evolving model capabilities, harnesses, tools, and...

PrivDev: Mapping Static-Analysis Data Types to DPV

Static-analysis scanners can identify personal-data types in source code, but they lack mechanisms to connect these findings to standardized privacy vocabularies. PrivDev maps 122 Bearer CLI data types to Data Privacy Vocabulary Personal Data DPV-PD categories and links them to potentially releva...

Apache HTTP Server 2.4.68 mod_vhost_alias Stack Overflow

Apache HTTP Server versions through 2.4.68 contain a stack-based buffer overflow in modvhostalias when VirtualDocumentRoot uses a hostname format specifier and LimitRequestFieldSize is raised above the default. The supplied tool performs a non-intrusive version check using the Server header...

A Secure DToF LiDAR SoC with Dual-Domain Fingerprinting and Event-Driven AFE Circuit Achieving Sensor-Level Attack Resilience

Recent studies have shown that most commercial direct time-of-flight dToF LiDARs can be spoofed by injecting high-frequency laser pulses into the receiver, which can erase pedestrians from the point cloud. This paper presents the first dToF LiDAR system-on-chip SoC with integrated sensor-level...

Quantum Fire with Delegated Cloning

Quantum fire is a recently introduced cryptographic primitive consisting of efficiently preparable quantum states, called flames, that admit efficient cloning but resist efficient telegraphing, namely reconstruction via classical communication without preshared entanglement. In all prior...

Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks

Security benchmarks for LLM-based agents often report the attack success rate ASR as a measure of model robustness and use these scores to compare different models and defense mechanisms, assuming that they describe the security of the agent. In this paper, we explore whether it also influences t...

AgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing Agents

Autonomous penetration testing agents conduct multi-step attacks by continuously adapting their plans and actions to target responses. As a common defense, honeypots can be deployed to divert these agents from real assets by presenting decoy services, while also supporting attack tracing and acti...

Beyond Predefined Sinks: Security-Aware Dependency Analysis for LLM Agents

Large language model LLM-based agents increasingly connect model-generated decisions to security-sensitive software capabilities such as command execution, filesystem access, network communication, browser control, and external tools. Existing analyses often use predefined sensitive operations as...

Constant-Rate Certified Deletion

We present a unified framework for upgrading a broad class of cryptographic primitives to support constant-rate certified deletion. Previous constructions require a linear number of qubits per encrypted bit of certified-deletable plaintext. In contrast, we obtain the first constant-rate...

Apache Tomcat 11.0.2 Vulnerability Scanner

Apache Tomcat versions 9.0.0 through 9.0.98, 10.1.0 through 10.1.34, and 11.0.0 through 11.0.2 may allow remote code execution when partial PUT and persistent sessions are enabled. The supplied Nuclei template identifies affected versions and tests partial PUT support...

Securing Computer-Use Agents against Branch Steering Attacks

Modern Computer Use Agents CUAs directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect prompt injection across every rendered page and tool response. While the Dual-LLM pattern is the primary system-level architecture offering formal security...

Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation

Mechanistic edits ablations, weight edits, activation steering are the standard tools for unlearning a harmful capability from a neural network while preserving useful ones. Current approaches validate their effects only by testing, which can never cover an entire continuous region of inputs. Pri...

Defense-In-Depth at the Perception-Reasoning Interface of LLM-Centric Agentic UAV Swarms

Large Language Models LLMs increasingly support Uncrewed Aerial Vehicle UAV swarm operations such as data collection scheduling, where the model reads structured sensor reports and decides which sensors to visit. An adversary who quietly manipulates those reports can redirect the swarm without...

SecJev: Bringing Security Expertise to System One Decision Models

Security workflows need models that turn complex observations and explicit policies into decisions. System One models introduced by Jev return typed predictions and probabilities; security specialization supplies the domain expertise behind those predictions. We introduce SecJev, to our knowledge...

Joern 4.0.645

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

CorrectGuard: Eyes-Off Correctness Estimation for Black-Box Security Guardrails

AI services increasingly rely on black-box security guardrails, yet privacy-preserving model auditing regimes often cannot measure how well these systems perform in both a human eyes-off production setting, which disallows human inspection of user input, and a machine eyes-off setting, which...

Reversing the Clock: Layout-Aware Recovery of Design Intent from Clock Distribution Networks

Hardware reverse engineering supports competitive analysis and hardware assurance by recovering information about an integrated circuit IC from its physical implementation. While existing techniques primarily recover the gate-level netlist, which represents logical functionality, they often...

Quantum Key Distribution with Entanglement-Swapped Photons from a Quantum Emitter

Quantum key distribution QKD is a fundamental functionality of quantum networks. Extending its range requires quantum repeaters, a technology still under development and not yet demonstrated in combination with quantum cryptographic protocols. Here, we address the elementary operation of a viable...

WordPress Authorizer 3.15.3 Privilege Escalation Scanner

WordPress Authorizer versions through 3.15.3 contain an unauthenticated privilege escalation vulnerability. The supplied Python tool passively detects installed versions and optionally inspects Azure OAuth2 configuration...

Containing the Autonomous Operator: A Defense-In-Depth Framework and Reference Architecture for Securing AI Agents on Kubernetes

Large language model LLM agents are moving from chat interfaces into infrastructure operations, where they read telemetry, call tools, generate and execute code, and change the state of production Kubernetes clusters. This collapses a boundary that conventional cloud-native security assumes: the...