AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current agent alignment frameworks inadequate for real-world...

Information Security in Small-Scale Protests: Surveillance of Ugandan Anti-EACOP Protesters

We examine the information security practices of Ugandan climate activists protesting the development of the East African Crude Oil Pipeline EACOP. We conducted five-week fieldwork in Kampala, Uganda, which included interviews with 13 anti-EACOP activists. Through an inductive analysis, we report...

Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation against Emerging Prompt Injection Attacks

Polymorphic Prompt Assembling PPA defends LLM agents against prompt injections by randomly selecting separator pairs from a fixed pool to isolate user input from system instructions. Although effective, static pool reuse exposes a blast-radius vulnerability: once a separator leaks, it can be...

An Organization-Scoped LLM Agent Runtime Architecture for Regulated Cybersecurity Operations

Regulated cybersecurity workflows lack a runtime substrate that enforces organization-level scope across retrieval, tool calls, memory, findings, reports, and audit while remaining model-agnostic and locally deployable. Recent large language model LLM agent systems report strong results on isolat...

DeepFake Forensics AI: A Multi-Modal Detection and Blockchain-Anchored Evidence Management Platform

The proliferation of AI-generated synthetic media poses a critical threat to the integrity of digital evidence in legal and forensic contexts. Existing deepfake detection systems typically address a single modality and provide no mechanism for tamper-proof evidence preservation. We present DeepFa...

Investigating Detection and Obfuscation of Prompt Injection Attacks against Software Reverse Engineering AI Agents

Agentic software reverse engineering systems are vulnerable to prompt injection attacks placed into the source code of executable binary files. This research demonstrates defensive tactics for detecting the presences of prompt injection strings in the decompiler output of adversarial example...

YARA-X 1.17.0

YARA-X is a re-incarnation of YARA, a pattern matching tool designed with malware researchers in mind. This new incarnation intends to be faster, safer and more user-friendly than its predecessor. The ultimate goal of YARA-X is replacing YARA as the default pattern matching tool for malware...

Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs

LLM-based coding assistants are seeing rapid adoption, offering substantial gains in developer productivity. As organizations increasingly ship code these agents produce, the security of that code becomes critical. Prior work has shown that minor prompt perturbations degrade the functional...

Protecting On-Device AI Inference: A Systematic Review of Attacks and Defence Mechanisms

The need for secure and private Artificial Intelligence AI and Machine Learning ML on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an ever-increasing number of pre-trained AI models being used o...

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models

As Large Language Models evolve for user convenience, vulnerability to jailbreak attacks continues to be reported despite ongoing efforts in safety training. Traditional jailbreak techniques typically focus on a single prompt injection, neglecting the models' ability to remember the flow of...

Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection

We show that LoRA adapters, the dominant distribution format for fine-tuned LLMs, can be reliably backdoored through training data poisoning while preserving baseline task performance. On a Qwen 2.5 1.5B prompt-injection classifier, a small fraction of poisoned examples drives a...

Automatically Attacking Software Reverse Engineering AI Agents

Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis without having access to original source code. Coupled with the analytic power of large language models LLM, agentic systems enabled with tools, such as...

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations

In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations at each transformer block. We find that refusal is linearly decodable well before the final layer, indicating that...

The Importance of Out-Of-Band Metadata for Safe Autonomous Agents: The Redpanda Agentic Data Plane

AI agents are increasingly expected to operate as digital employees: accessing enterprise data, making decisions, and taking actions autonomously. But agents are simultaneously less predictable than humans -- prone to hallucination, misinterpretation, and adversarial manipulation -- and more...

SAMD: A Tool for Identifying False Data Injection Scenarios in AI/ML-Enabled Medical Devices

The growing integration of artificial intelligence AI and machine learning ML in medical systems requires effective measures to address emerging security risks. One such risk is that of adversaries introducing false data through vulnerable system components during inference, causing misdiagnosis...

Cybersecurity AI (CAI) Dataset

We present CAI Dataset, a fourteen-month corpus of cybersecurity LLM trajectories collected through the open-source CAI agent framework, built in response to PentestGPT's finding that expert operator trajectories, not base-model capability, are the bottleneck for cybersecurity LLM performance. CA...

Relevance As a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms that govern model outputs. Prior work shows that enabling...

angr 9.2.219

angr is an open-source binary analysis platform for Python. It combines both static and dynamic symbolic "concolic" analysis, providing tools to solve a variety of tasks...

A Wolf in Sheep'S Clothing: Targeted Routing Hijacking in Federated RAG

Federated Retrieval-Augmented Generation FedRAG is attractive for privacy-sensitive applications because raw data remain local. As a result, routing must rely on client-provided semantic profiles, creating a new opportunity for manipulation. We introduce Routing Hijacking, a routing-stage attack ...

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

We analyzed 3,984 AI agent skills from major marketplaces and found 76 confirmed malicious payloads, including credential theft, backdoor installation, and data exfiltration. 13.4% of all skills contain at least one critical-level security issue and at least 8 manually confirmed malicious skills...

S3C2 Summit 2025-07: Government Secure Supply Chain Summit

Software supply chains, while providing immense economic and software development value, are only as strong as their weakest link. Over the past several years, there has been an exponential increase in cyberattacks specifically targeting vulnerable links in critical software supply chains. The...

Towards Demystifying and Repairing LLM-In-The-Loop Vulnerabilities

Large Language ModelsLLMs have been actively integrated into modern software systems as critical components. LLM-in-the-loop vulnerabilities, where vulnerabilities are introduced by LLMs and their dependent downstream components, such as frameworks, introduce new risks. Although some benchmark...

Measuring Real-World Prompt Injection Attacks in LLM-Based Resume Screening

LLMs are vulnerable to prompt injection attacks. However, this vulnerability has been primarily demonstrated conceptually in academic studies or through a few anecdotal case studies. Its prevalence and impact in real-world LLM-based applications are largely unexplored. In this work, we present th...

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents Via User-Generated Content

Mobile graphical user interface GUI agents driven by vision-language models VLMs perceive the screen as rendered pixels and choose actions from what they see, so they cannot reliably separate trusted interface elements from user-generated content. We present MIRAGE Mobile Injection of Realistic...

Joern 4.0.548

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...

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking

Jailbreak attacks on large language models LLMs aim to induce LLMs to produce content that they are expected to refuse. Automated black-box jailbreak generation is especially important for safety evaluation, where the attacker observes only model outputs and needs to automatically search for...

HunterAgent: Neuro-Symbolic Attack Trace Reconstruction under Anti-Forensics

Modern alert-triage systems reduce SOC burden by filtering false positives, but flagging a high-risk alert is only the start of incident response. Threat hunting requires reconstructing causal attack chains across heterogeneous, partially corrupted logs. Against APTs using anti-forensics parent-P...

Efficient and Quantum-Safe Internet Key Exchange Protocols for Satellite Communications

This paper studies cryptographic key exchange in satellite communications, which requires specific solutions because the satellite context presents unique challenges, particularly concerning onboard resource constraints and long transmission latency. We address these challenges by considering the...

Towards Cybersecurity SuperIntelligence (CSI): What'S the Best Harness for Cybersecurity?

What is the best harness for cybersecurity AI? Cybersecurity systems are converging on a single execution scaffold per agent, an iterative shell loop driven by a Large Language Model LLM. However, scaffolds are not interchangeable, rarely interoperable, and no single scaffold dominates across all...

Do You Dare to Try Test-Driven Forensics? Increasing Trust in Desktop Forensics with ADARE

Digital forensic relies on validated tools and established procedures, yet the underlying operating systems, applications, and analysis tools evolve rapidly. This evolution can cause artifact behavior and tool outputs to drift, silently degrading repeatability and confidence in long-lived forensi...

OSSEC HIDS 4.1.0

OSSEC is a full platform to monitor and control your systems. It mixes together all the aspects of HIDS host-based intrusion detection, log monitoring and SIM/SIEM together in a simple, powerful and open source solution. This is the source code release...

Anonymous YARA Rules Are Not Anonymous

YARA rules are widely shared across threat intelligence communities to enable collective defence against malware. This practice implicitly assumes that removing metadata e.g., author fields sufficiently protects the identity of contributing organisations. To assess the validity of this assumption...

Silent Consent, Persistent Risk: Android Permission Groups and Custom Permissions

Android's permission system is designed to balance usability with informed consent, yet two legacy mechanisms still undermine that balance in Android 16: i permission groups that silently auto-grant new permissions within a group after a user's initial approval, and ii normal-level custom...

The Fault in Our Drafts: Vulnerabilities in RPKI Specification and Software

The Resource Public Key Infrastructure RPKI secures the Internet's routing system by defining a complex trust and validation framework for certificates, Route Origin Authorizations ROAs, manifests, and Certificate Revocation Lists CRLs. These mechanisms are specified across dozens of RFCs. This...

SEC-Bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

Large language models LLMs now support automated software security tasks, including vulnerability discovery and proof-of-concept PoC generation. Existing benchmarks do not faithfully evaluate LLMs in real-world bug hunting scenarios because they rely on fuzzing harnesses, target-specific...

Meta-Quantum Ensemble Framework for Robust Network Intrusion Detection

Intrusion Detection Systems IDSs must maintain high detection sensitivity while operating under strict false-positive constraints, a challenge intensified by class imbalance and heterogeneous IoT traffic. This work investigates whether heterogeneous quantum learners can provide useful and...

Local Privacy Laws in a Globalized World

Personal data has emerged as a highly valuable yet sensitive asset that drives business decisions, enables targeted advertising, and generates substantial revenue for companies, while simultaneously facilitating invasive monitoring of users. In recent years, research on digital privacy violations...

Anthropic / Microsoft MCP Server-Side Request Forgery

Both Anthropic mcp-server-fetch and Microsoft playwright-mcp suffer from server-side request forgery vulnerabilities by accepting arbitrary URLs passed by the AI agent/client without any allowlist enforcement, IP range blocking, or internal network filtering...

BAIT: Boundary-Guided Disclosure Escalation Via Self-Conditioned Reasoning

In this work, we propose BAIT Boundary-Aware Iterative Trap, a three-step jailbreak framework that approaches malicious goals through internal disclosure. BAIT first asks the model to identify the protection boundary, then requires it to refine that boundary, and finally requests a detailed...

HammerSim: A System-Level Tool to Model RowHammer

Modern architecture research relies on simulators to evaluate system security, yet analyzing emerging hardware vulnerabilities like RowHammer requires full-system visibility. As RowHammer vulnerabilities worsen with continuous technology scaling, existing simulators lack the system-level models...

Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security

Large Language Models LLMs are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt injection, pose significant risks to the integrity and...

Falco 0.44.0

Sysdig Falco is a behavioral activity monitoring agent that is open source and comes with native support for containers. Falco lets you define highly granular rules to check for activities involving file and network activity, process execution, IPC, and much more, using a flexible syntax. Falco...

MRMMIA: Membership Inference Attacks on Memory in Chat Agents

Membership inference attacks MIAs test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine learning systems. Prior work has primarily focused on training corpora or retrieval databases. However, MIAs against agent...

Lessons from Penetration Tests on Large-Scale Agent Systems

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes of weaknesses long observed in prior computing systems...

Batch Me If You Can: Coverage-Guided RPKI Fuzzing at Scale

The Resource Public Key Infrastructure RPKI has become essential to secure inter-domain routing. Despite its critical role, RPKI software remains largely untested beyond shallow parsing. Existing fuzzers, like AFL++ or libFuzzer, do not work well for RPKI as they assume a single, self-contained...

A Surveillance Evasion Game with Continuous Sensor Redeployment Via Bilevel Optimization

Uncrewed Aerial Systems UASs have become a growing threat to the security of critical infrastructure, exploiting spatiotemporal gaps in sensor perimeters to infiltrate restricted airspace undetected. We formulate this interaction as a two-player zero-sum differential game between an adversarial U...

Backdoor Attacks on Fault Detection and Localization in Cyber-Physical Systems

Cyber-Physical Systems CPS integrate sensing, communication, computation, and control to support critical infrastructure, including smart grids, industrial automation, and control systems. In the electrical utility domain, various controllers are used in CPS to ensure the system detects and...

TTPrint: Evidence-Grounded TTP Extraction Via Diverge-Then-Converge Verification

Extracting MITRE ATT&CK techniques from cyber threat intelligence CTI reports is an open-set, multi-label problem requiring both high recall not missing techniques and high precision not hallucinating unsupported ones. Existing methods--rule-based, supervised, and LLM-based--struggle to achieve...

"What Is the Problem Space?" Defining Host-Space Adversarial Perturbations against Network Intrusion Detection Systems

Network Intrusion Detection Systems NIDS are now increasingly leveraging Machine Learning ML techniques to detect malicious network activities. Numerous papers have scrutinized the security of ML-based NIDS ML-NIDS by testing them against various attacks involving adversarial perturbations. The...

FuzzPilot: Plateau-Triggered Recipe Validation for Structured Text Fuzzing

FuzzPilot is a controller for AFL++ that moves expensive reasoning out of the mutation hot path. When coverage plateaus, it snapshots the corpus, prepares candidate mutation recipes, evaluates them in short isolated AFL++ micro-campaigns, and promotes only recipes with positive validation reward...