The Pentagon Knew Enemies Could Track Troops’ Phones for Years. Now They Are

The US military has long known that cheap fixes could stop location data from exposing its troops. It adopted almost none—and now says adversaries are using the data to target soldiers during a war...

AI-Driven Adaptive Adversaries and the Erosion of Cryptographic Trust in Public Key Systems

This paper examines the erosion of Public Key Cryptography PKC security under adaptive adversarial optimisation driven by artificial intelligence. The problem addressed is the growing mismatch between algorithm-centric cryptographic security models and operational attack realities, where...

Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries

Agentic AI governance is a critical component of agentic AI infrastructure ensuring that agents follow their owner's communication and interaction policies, and providing protection against attacks from malicious agents. The state-of-the-art solution, SAGA, assumes a logically centralized point o...

Operationalizing Cybersecurity Governance for Mitigation Planning with Attack-Path Modeling and Reinforcement Learning

We address a fundamental challenge in cybersecurity operations of translating governance frameworks into actionable mitigation decisions under realistic resource constraints. Frameworks such as the NIST Cybersecurity Framework CSF provide widely adopted measures of organizational maturity, but do...

ARGUS: Defending LLM Agents against Context-Aware Prompt Injection

The rise of Large Language Model LLM agents, augmented with tool use, skills, and external knowledge, has introduced new security risks. Among them, prompt injection attacks, where adversaries embed malicious instructions into the agent workflow, have emerged as the primary threat. However,...

Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspective

Machine learning-based malware detectors are increasingly vulnerable to adversarial examples. Traditional defenses, such as one-shot adversarial training, often fail against adaptive attackers who use reinforcement learning to bypass detection. This paper proposes a robust defense framework based...

TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models

The deployment of Large Reasoning Models LRMs in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought CoT is manipulated to provide a linguistically plausible but logically fallacio...

CVE-2019-11642

A log poisoning vulnerability has been discovered in the OneShield Policy Dragon Core framework before 5.1.10. Authenticated remote adversaries can poison log files by entering malicious payloads in either headers or form elements. These payloads are then executed via a client side debugging...

EUVD-2019-3312

Malware in sbrugna...

EUVD-2020-5136

Malware in sbrugna...

EUVD-2020-5137

Malware in sbrugna...

Cyber Warfare during Operation Sindoor: Malware Campaign Analysis and Detection Framework

Rapid digitization of critical infrastructure has made cyberwarfare one of the important dimensions of modern conflicts. Attacking the critical infrastructure is an attractive pre-emptive proposition for adversaries as it can be done remotely without crossing borders. Such attacks disturb the...

Optimal Untelegraphable Encryption and Implications for Uncloneable Encryption

We investigate the notion of untelegraphable encryption UTE, a quantum encryption primitive that is a special case of uncloneable encryption UE, where the adversary's capabilities are restricted to producing purely classical information rather than arbitrary quantum states. We present an...

On Post-Quantum Cryptography Authentication for Quantum Key Distribution

The traditional way for a Quantum Key Distribution QKD user to join a quantum network is by authenticating themselves using pre-shared key material. While this approach is sufficient for small-scale networks, it becomes impractical as the network grows, due to the total quadratic increase in the...

Beyond the Worst Case: Extending Differential Privacy Guarantees to Realistic Adversaries

Differential Privacy DP is a family of definitions that bound the worst-case privacy leakage of a mechanism. One important feature of the worst-case DP guarantee is it naturally implies protections against adversaries with less prior information, more sophisticated attack goals, and complex...

Dynamic Risk Assessments for Offensive Cybersecurity Agents

Foundation models are increasingly becoming better autonomous programmers, raising the prospect that they could also automate dangerous offensive cyber-operations. Current frontier model audits probe the cybersecurity risks of such agents, but most fail to account for the degrees of freedom...

Benchmarking Misuse Mitigation against Covert Adversaries

Existing language model safety evaluations focus on overt attacks and low-stakes tasks. Realistic attackers can subvert current safeguards by requesting help on small, benign-seeming tasks across many independent queries. Because individual queries do not appear harmful, the attack is hard to...

CVE-2020-12854

A remote code execution vulnerability was identified in SecZetta NEProfile 3.3.11. Authenticated remote adversaries can invoke code execution upon uploading a carefully crafted JPEG file as part of the profile avatar...

Alignment under Pressure: the Case for Informed Adversaries When Evaluating LLM Defenses

Large language models LLMs are rapidly deployed in real-world applications ranging from chatbots to agentic systems. Alignment is one of the main approaches used to defend against attacks such as prompt injection and jailbreaks. Recent defenses report near-zero Attack Success Rates ASR even again...

Linux Distros Unpatched Vulnerability : CVE-2024-37303

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - Synapse is an open-source Matrix homeserver. Synapse before version 1.106 allows, by design, unauthenticated remote participants to trigger a download and cachi...