Explainability-Guided Adversarial Attacks on Transformer-Based Malware Detectors Using Control Flow Graphs

Transformer-based malware detection systems operating on graph modalities such as control flow graphs CFGs achieve strong performance by modeling structural relationships in program behavior. However, their robustness to adversarial evasion attacks remains underexplored. This paper examines the...

AEGIS: Adversarial Entropy-Guided Immune System -- Thermodynamic State Space Models for Zero-Day Network Evasion Detection

As TLS 1.3 encryption limits traditional Deep Packet Inspection DPI, the security community has pivoted to Euclidean Transformer-based classifiers e.g., ET-BERT for encrypted traffic analysis. However, these models remain vulnerable to byte-level adversarial morphing -- recent pre-padding attacks...

SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants

LLM-based multi-agent systems MASs are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the potential of locally deployed agents integrated with personal data and services, but this autonomy introduces significant...

Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models

Large language models LLMs increasingly rely on explicit chain-of-thought CoT reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work on LLM safety focuses on content safety--detecting harmful, biased, or factually incorrect...

Toward a Multi-Layer ML-Based Security Framework for Industrial IoT

The Industrial Internet of Things IIoT introduces significant security challenges as resource-constrained devices become increasingly integrated into critical industrial processes. Existing security approaches typically address threats at a single network layer, often relying on expensive hardwar...

Security Barriers to Trustworthy AI-Driven Cyber Threat Intelligence in Finance: Evidence from Practitioners

Financial institutions face increasing cyber risk while operating under strict regulatory oversight. To manage this risk, they rely heavily on Cyber Threat Intelligence CTI to inform detection, response, and strategic security decisions. Artificial intelligence AI is widely suggested as a means t...

Targeted Adversarial Traffic Generation : Black-Box Approach to Evade Intrusion Detection Systems in IoT Networks

The integration of machine learning ML algorithms into Internet of Things IoT applications has introduced significant advantages alongside vulnerabilities to adversarial attacks, especially within IoT-based intrusion detection systems IDS. While theoretical adversarial attacks have been extensive...

Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks

Retrieval-Augmented Generation RAG significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases. However, the multi-module architecture of RAG introduces complex system-level security vulnerabilities. Guided by the R...

T-MAP: Red-Teaming LLM Agents with Trajectory-Aware Evolutionary Search

While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models LLMs, such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in rapidly growing ecosystems such as the Model Context Protoc...

Measuring and Exploiting Confirmation Bias in LLM-Assisted Security Code Review

Security code reviews increasingly rely on systems integrating Large Language Models LLMs, ranging from interactive assistants to autonomous agents in CI/CD pipelines. We study whether confirmation bias i.e., the tendency to favor interpretations that align with prior expectations affects LLM-bas...

What is CTEM? A Modern Approach to Cyber Risk

To effectively defend your organization, you need to think like an attacker. Attackers don’t care about a vulnerability’s CVSS score; they care about whether they can exploit it to reach a valuable target. Traditional security often misses this crucial context, leaving you to guess which of the...

AI is Everywhere, But CISOs are Still Securing It with Yesterday's Skills and Tools, Study Finds

A majority of security leaders are struggling to defend AI systems with tools and skills that are not fit for the challenge, according to the AI and Adversarial Testing Benchmark Report 2026 from Pentera. The report, based on a survey of 300 US CISOs and senior security leaders, examines how...

Security Assessment and Mitigation Strategies for Large Language Models: A Comprehensive Defensive Framework

Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive comparative security assessment exists across major LLM...

Experimental Evaluation of Security Attacks on Self-Driving Car Platforms

Deep learning-based perception pipelines in autonomous ground vehicles are vulnerable to both adversarial manipulation and network-layer disruption. We present a systematic, on-hardware experimental evaluation of five attack classes: FGSM, PGD, man-in-the-middle MitM, denial-of-service DoS, and...

manchurian-agent-poc

Manchurian Candidate Agent POC ⚠️ SECURITY RESEARCH — EDU...

Researchers Trick Perplexity's Comet AI Browser Into Phishing Scam in Under Four Minutes

Agentic web browsers that leverage artificial intelligence AI capabilities to autonomously execute actions across multiple websites on behalf of a user could be trained and tricked into falling prey to phishing and scam traps. The attack, at its core, takes advantage of AI browsers' tendency to...

PT-2026-36198

Name of the Vulnerable Software and Affected Versions Exim versions prior to 4.99.2 Description When the SPA authentication driver is used with an adversarial SPA resource, an out-of-bounds write can occur, leading to a crash of the connection instance. Additionally, erroneous data processing may...

Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks

Adversarial examples can represent a serious threat to machine learning ML algorithms. If used to manipulate the behaviour of ML-based Network Intrusion Detection Systems NIDS, they can jeopardize network security. In this work, we aim to mitigate such risks by increasing the robustness of NIDS...

Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw

Code agents powered by large language models can execute shell commands on behalf of users, introducing severe security vulnerabilities. This paper presents a two-phase security analysis of the OpenClaw platform. As an open-source AI agent framework that operates locally, OpenClaw can be integrat...

Adversarial Reinforcement Learning for Detecting False Data Injection Attacks in Vehicular Routing

In modern transportation networks, adversaries can manipulate routing algorithms using false data injection attacks, such as simulating heavy traffic with multiple devices running crowdsourced navigation applications, to mislead vehicles toward suboptimal routes and increase congestion. To addres...