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...

Analyzing Concentration, Temporal Routines and Targeting in Public Ransomware Leak Site Data

Ransomware has grown to become one of the most damaging types of cybercrime, affecting private and public organizations in any sector. While early types of ransomware targeted many victims via automated attacks, ransomware groups have started to specifically target organizations and companies in...

Profiling User Vulnerability to Phishing through Psychological and Behavioral Factors

Phishing remains one of the most pervasive cybersecurity threats, shifting the focus from technological vulnerabilities to human cognitive and psychological factors. In coherence with the trend of studies on phishing to increasingly focus on human aspects and vulnerable users profiling, this stud...

Detecting Data Exfiltration through I2P Anonymity Networks: A Two-Phase Machine Learning Approach

The Invisible Internet Project I2P provides strong anonymity through garlic routing and distributed network architecture, making it attractive for legitimate privacy needs. Nevertheless, the same properties can be exploited by malicious actors to steal sensitive information from corporate network...

Behavioral Integrity Verification for AI Agent Skills

Agent skills extend LLM agents with privileged third-party capabilities such as filesystem access, credentials, network calls, and shell execution. Existing safety work catches malicious prompts and risky runtime actions, but the skill artifact itself goes unverified. We formalize this as the...

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous OS-level operations with irreversible consequences. Existing...

Improper Enforcement of Behavioral Workflow

Overview YAFNET.Core is an Open Source Forum solution! The YAF.NET project is an international collaboration of like-minded, skilled, and creative individuals who are striving to make YAF.NET the most robust and malleable forum solutions available. Affected versions of this package are vulnerable...

Trident: Improving Malware Detection with LLMs and Behavioral Features

Traditionally, machine learning methods for PE malware detection have relied on static features like byte histograms, string information, and PE header contents. One barrier to incorporating dynamic analysis features has been the semi-structured nature of sandbox behavior reports. We show that,...

Constraint-Guided Multi-Agent Decompilation for Executable Binary Recovery

Decompilation -- recovering source code from compiled binaries -- is essential for security analysis, malware reverse engineering, and legacy software maintenance. However, existing decompilers produce code that often fails to compile or execute correctly, limiting their practical utility. We...

net_exploit_detector

netexploitdetector.py Behavioral network exploit detector f...

Security Is Relative: Training-Free Vulnerability Detection Via Multi-Agent Behavioral Contract Synthesis

Deep learning for vulnerability detection has shown promising results on early benchmarks, but recent evaluations reveal catastrophic degradation: models achieving F1 0.68 on legacy datasets collapse to 0.031 under strict deduplication. We identify the root cause as the semantic ambiguity problem...

How A Simple Misconfiguration Can Fuel Offline Attacker Tools

How A Simple Misconfiguration Can Fuel Offline Attacker Tools By Grant McDonald · April 9, 2026 It’s no secret that misconfigurations are a gateway for attackers. But that doesn’t mean misconfigurations won’t happen or that attackers won’t attempt to exploit them. In the latest research from our...

Digital Privacy in IoT: Exploring Challenges, Approaches and Open Issues

Privacy has always been a critical issue in the digital era, particularly with the increasing use of Internet of Things IoT devices. As the IoT continues to transform industries such as healthcare, smart cities, and home automation, it has also introduced serious challenges regarding the security...

From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers

The model context protocol MCP standardizes how LLMs connect to external tools and data sources, enabling faster integration but introducing new attack vectors. Despite the growing adoption of MCP, existing MCP security studies classify attacks by their observable effects, obscuring how attacks...

The Importance of Behavioral Analytics in AI-Enabled Cyber Attacks

Artificial Intelligence AI is changing how individuals and organizations conduct many activities, including how cybercriminals carry out phishing attacks and iterate on malware. Now, cybercriminals are using AI to generate personalized phishing emails, deepfakes and malware that evade traditional...

Everyday tools, extraordinary crimes: the ransomware exfiltration playbook

Data exfiltration activity increasingly leverages legitimate native utilities, commonly deployed third-party tools, and cloud service clients, reducing the effectiveness of static indicators of compromise IOCs and tool-based blocking strategies. The Exfiltration Framework systematically normalize...

EUVD-2025-208658

IBM Aspera Console 3.3.0 through 3.4.8 could allow a privileged user to cause a denial of service due to improper enforcement of behavioral workflow...

CVE-2025-13459

IBM Aspera Console 3.3.0 through 3.4.8 could allow a privileged user to cause a denial of service due to improper enforcement of behavioral workflow...

AegisUI: Behavioral Anomaly Detection for Structured User Interface Protocols in AI Agent Systems

AI agents that build user interfaces on the fly assembling buttons, forms, and data displays from structured protocol payloads are becoming common in production systems. The trouble is that a payload can pass every schema check and still trick a user: a button might say "View invoice" while its...

EUVD-2026-9335

HomeBox is a home inventory and organization system. Prior to 0.24.0-rc.1, the notifier functionality allows authenticated users to specify arbitrary URLs to which the application sends HTTP POST requests. No validation or restriction is applied to the supplied host, IP address, or port. Although...