Opening Forensia workspaceacquiring
Loading the current evidence view. Navigation and account controls remain available.
Loading recent evidenceacquiring
Intelligence reports
Loading the current evidence view. Navigation and account controls remain available.
Ordering reports and their extracted indicators.
Applying the current filters and ordering.
Forensia intelligence desk · 4,100 source documents · 4,068 stories
Live reporting, advisories and research arranged by editorial readiness. Thin sources stay visible, but they are clearly marked instead of being presented as complete analysis.
On this page
40 documents
Briefs ready now
40
Multi-source clusters
2
Publisher text withheld
15
CryptoJS Weak RNG Behind $5.7 Million in Drains Affects Five Crypto Wallet Apps
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Apple iCloud Private Relay Can Expose Real IPs Through WebKit Proxy Bypasses
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Critical Paperclip Flaw Allowed Admin Access, Code Execution
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Token Jacking: Cybercriminals Could Be Stealing Your AI Resources
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Meta AI Hacked External Systems During Cybersecurity Testing
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Belarusian Ransom Cartel Mastermind Gets 16 Years in Prison
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Attackers Compile khunt Inside Oracle to Turn SQL Injection Into Windows SYSTEM Access
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
AWS, Google, and Vercel Agent Flaws Let Attackers Trigger Tools Without Running the Model
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Chinese-Made Zbtlink Routers Ship With Backdoor That Opens Unauthenticated Root Shells
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Cisco Patches Critical SD-WAN, IOS XE, FMC Vulnerabilities
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Ransom Cartel Creator Gets 16 Years in Prison for Operating Ransomware-as-a-Service
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
CISA Flags TeamCity CVE-2026-63077 RCE Flaw Under Active Exploitation in the Wild
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Hackers Start Exploiting Recent JetBrains TeamCity Vulnerability
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Snowflake Hacker Pleads Guilty Over Breaches Affecting at Least 100 Million People
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
LoginTrap: Uncovering Task-Agnostic Phishing-Style Indirect Prompt Injection Attacks against LLM-based Web Agents
LoginTrap: Uncovering Task-Agnostic Phishing-Style Indirect Prompt Injection Attacks against LLM-based Web Agents arXiv:2608.04741v1 Announce Type: new Abstract: LLM-based web agents automate user tasks by observing webpages and executing browser actions on behalf of users. As these agents operate on real web services, login becomes a sensitive authentication boundary because it involves credentials and sensitive information. Existing work shows that malicious webpage conten…
MOAT: Model-Agnostic Randomized Transformations for preventing Efficiency Degradation Attacks on ViTs
MOAT: Model-Agnostic Randomized Transformations for preventing Efficiency Degradation Attacks on ViTs arXiv:2608.04680v1 Announce Type: new Abstract: To adopt the Vision Transformers (ViTs) in resource-constrained environment, token pruning is widely used to reduce computational cost without impacting accuracy. However, adversaries have developed targeted attacks against said token pruning techniques to undermine such attempts to make ViTs efficient. In this paper, we propos…
Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future Directions
Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future Directions arXiv:2608.04626v1 Announce Type: new Abstract: AI agents are evolving from isolated task executors into networked autonomous entities that can communicate, delegate tasks, invoke tools, access external knowledge, and participate in cross-platform service and economic workflows. This evolution gives rise to open agent networks, where heterogeneous agents owned by different stakehold…
Adaptive Intrusion Detection System using Transformer-Based Neural Networks and Continual Learning Approach with Adversarial Investigation
Adaptive Intrusion Detection System using Transformer-Based Neural Networks and Continual Learning Approach with Adversarial Investigation arXiv:2608.04602v1 Announce Type: new Abstract: Network intrusion detection systems (IDS) trained on fixed traffic snapshots decay silently after deployment as threat distributions shift. Fine-tuning models on new attacks triggers catastrophic forgetting, while retraining from scratch is computationally infeasible. Replay-based continual …
Breadcrumbing Search Agents
Breadcrumbing Search Agents arXiv:2608.04565v1 Announce Type: new Abstract: LLM-based search agents are widely used for information-seeking tasks, but their reliance on external tool returns introduces a critical security risk: web content retrieved during execution is untrusted, exposing agents to prompt injection and goal hijacking. Prior work on search-agent safety primarily focuses on static web-content injection, but modern agents issue follow-up queries and cross-check…
Checked-In Secret Detection: Strings Are All You Need
Checked-In Secret Detection: Strings Are All You Need arXiv:2608.04523v1 Announce Type: new Abstract: Hardcoded secrets in source code pose critical security vulnerabilities which can be easily exploited by malicious adversaries. Existing regex-based detection approaches suffer from fundamental limitations, as secrets often lack identifiable patterns, resulting in poor precision and recall. Recent studies have explored context-aware detection methods, as surrounding code can…
DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models
DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models arXiv:2608.04477v1 Announce Type: new Abstract: Cloud-based language model services routinely process prompts containing sensitive information. Obfuscation-based defenses---including ObfusLM, SentinelLMs, TextObfuscator, and DPNR---mitigate this risk by transforming prompt representations before transmission, offering a lightweight alternative to cryptographic solutions. We show these defenses…
Large Language Models and Social Media Information Integrity: Opportunities, Challenges, and Research Directions
Large Language Models and Social Media Information Integrity: Opportunities, Challenges, and Research Directions arXiv:2608.04375v1 Announce Type: new Abstract: Large Language Models (LLMs) have emerged as powerful tools that impact information integrity on social media platforms. This comprehensive review examines the dual role of LLMs in both facilitating and mitigating various information integrity challenges, including misinformation, disinformation, fake news, social bo…
Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework
Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework arXiv:2608.04366v1 Announce Type: new Abstract: While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption attacks. Adversaries exploit these vulnerabilities by poisoning documents provided by RAG system to manipulate LLM outputs. To counter this threat, w…
Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)
Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) arXiv:2608.04317v1 Announce Type: new Abstract: Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively against static, heuristic red agents, leaving their robustness against adaptive threats critically understudied. Meanwhile, recent advances in Reinforcement Learning with Verifiable Rewards (R…
Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle
Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle arXiv:2608.04314v1 Announce Type: new Abstract: Once visual content enters an AI pipeline, its owner often retains little technical control over how it is used. Legal and regulatory remedies can address misuse, but many technical interventions must be applied earlier, when content is released or accessed. This survey examines the protective paradigm that has grown around this i…
PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration
PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration arXiv:2608.04255v1 Announce Type: new Abstract: Graph inference over relational data can expose sensitive edge information, and this risk becomes more severe in dynamic graphs, where repeated model updates cause privacy loss to accumulate. We formulate Edge-level Differentially Private Dynamic Graph Inference (EDG) and propose PriDyG, a private inference framework that combines GNN-based structural…
Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills
Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills arXiv:2608.04192v1 Announce Type: new Abstract: Closed source agent skills may encode proprietary instructions, scripts, constants, and data. Providers may offer their capabilities as services while keeping the underlying packages hidden. Prior work focuses on prompt injection attacks that directly disclose these artifacts, and existing defenses accordingly aim to prevent such leakage.…
Open-World Darknet Traffic Recognition Under Leave-One-Service-Out Evaluation
Open-World Darknet Traffic Recognition Under Leave-One-Service-Out Evaluation arXiv:2608.04167v1 Announce Type: new Abstract: Darknet traffic recognition is critical for cyber threat intelligence, as anonymity networks are often used to conceal malicious activity. However, most existing studies rely on closed-world evaluation, assuming all service categories are known during training and testing, which is unrealistic in real-world environments. This paper presents an open-wo…
Behavioral Information Leakage in Darknet Traffic: A Multi-Channel Analysis Across Anonymity Networks
Behavioral Information Leakage in Darknet Traffic: A Multi-Channel Analysis Across Anonymity Networks arXiv:2608.04143v1 Announce Type: new Abstract: Existing darknet traffic classification studies largely emphasize predictive accuracy while offering limited insight into the behavioral mechanisms that make encrypted services distinguishable. This paper proposes a behavioral information leakage framework that decomposes flow-level traffic into control, structural, and rhythmi…
NEBULA: A Language - Independent Specification for Opaque Rotating Refresh Tokens
NEBULA: A Language - Independent Specification for Opaque Rotating Refresh Tokens arXiv:2608.04115v1 Announce Type: new Abstract: Refresh tokens are among the most sensitive credentials in modern authentication systems: long-lived, bearer-style, and sufficient to mint access tokens for days or weeks. RFC 9700, the current Best Current Practice for OAuth 2.0 security, mandates that refresh tokens issued to public clients be rotated on every use with replay (reuse) detection, …
FBID: Adaptive Personalized Federated Learning for Robust Out-of-Distribution Attack Detection in IoT Networks
FBID: Adaptive Personalized Federated Learning for Robust Out-of-Distribution Attack Detection in IoT Networks arXiv:2608.04073v1 Announce Type: new Abstract: Personalized Federated Learning (PFL) has emerged as a promising solution for intrusion detection in heterogeneous IoT environments, as it can improve local adaptation under highly Non-Independent and Identically Distributed (non-IID) data distributions. However, existing PFL methods often rely on client-side self-adju…
An Inline Control Architecture for Language Models in Intelligent Transportation Systems
An Inline Control Architecture for Language Models in Intelligent Transportation Systems arXiv:2608.04065v1 Announce Type: new Abstract: Vehicle-to-everything (V2X) systems increasingly incorporate large language models (LLMs) for semantic tasks such as message summarization, operator assistance, and decision support at roadside units and edge nodes. Although these components are not part of safety-critical control loops, they introduce prompt-level attack surfaces that are …
AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection
AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection arXiv:2608.04053v1 Announce Type: new Abstract: Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters. In practice, user requests are often underspecified: they describe the desired outcome without fully specifying acceptable behavior. An injection can exploit this ambiguity, causi…
When Modalities Fail to Tango: Conformal Backdoor Detection in Multimodal Contrastive Learning
When Modalities Fail to Tango: Conformal Backdoor Detection in Multimodal Contrastive Learning arXiv:2608.04052v1 Announce Type: new Abstract: Backdoor attacks in multimodal contrastive learning (MCL) have garnered growing attention in recent years, as many downstream tasks critically depend on pre-trained MCL models. Existing detection-based defenses predominantly rely on the CLIPScore metric, under the assumption that poisoned pairs exhibit lower semantic similarity betwee…
Beyond the QBER Threshold: A Temporal QBER Based Machine Learning Framework for Multi Attack Detection in BB84 QKD
Beyond the QBER Threshold: A Temporal QBER Based Machine Learning Framework for Multi Attack Detection in BB84 QKD arXiv:2608.04047v1 Announce Type: new Abstract: Conventional BB84 Quantum Key Distribution (QKD) systems rely on a fixed 11% Quantum Bit Error Rate (QBER) threshold to detect eavesdropping. However, stealthy attacks can remain below this threshold while still compromising channel security. This paper proposes a temporal QBER based machine learning framework for …
AMD SEV-SNP: A Confidential Computing Primer
AMD SEV-SNP: A Confidential Computing Primer arXiv:2608.04039v1 Announce Type: new Abstract: This paper is a technical primer on AMD Secure Encrypted Virtualization with Secure Nested Paging (SEV-SNP), a hardware confidential computing implementation that provides Trusted Execution Environments (TEEs) for virtual machines. SEV-SNP treats the hypervisor as adversarial. It encrypts guest memory and register state with keys the hypervisor never possesses, detects any tampering …
A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination
A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination arXiv:2608.04034v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive progress in image-text comprehension and generation, yet they remain susceptible to jailbreak attacks that can trigger harmful outputs and pose serious safety concerns. Existing multimodal jailbreak attacks have shown the feasibility of such attacks, but the…
SoK: How Frontier AI Reshapes System-Level Security Risk Dynamics in Critical Infrastructure
SoK: How Frontier AI Reshapes System-Level Security Risk Dynamics in Critical Infrastructure arXiv:2608.04033v1 Announce Type: new Abstract: Frontier artificial intelligence (FAI), encompassing large-scale, general-purpose AI systems, including large language models, multimodal foundation models, and agentic systems, is increasingly integrated into critical infrastructure (CI). This challenges long-standing security assumptions of bounded behavior, segmented networks, compon…
Securing Contrastive mmWave-based Human Activity Recognition against Adversarial Label Flipping
Securing Contrastive mmWave-based Human Activity Recognition against Adversarial Label Flipping arXiv:2608.04029v1 Announce Type: new Abstract: Wireless Human Activity Recognition (HAR), leveraging their non-intrusive nature, has the potential to revolutionize various sectors, including healthcare, virtual reality, and surveillance. The advent of millimeter wave (mmWave) technology has significantly enhanced the capabilities of wireless HAR systems. This paper presents the f…
story desk
clustered evidenceWatchGuard Patches Critical Vulnerabilities
developing · new
Microsoft Rolls Out 22 Fresh Security Patches
source only · new
Google Patches 6th Chrome Zero-Day of 2026
developing · new
Cisco Warns of Unpatched Secure Email Flaws, Patches Critical Switch Vulnerabilities
developing · new
Cisco Patches Critical Crosswork, Secure Workload Vulnerabilities
source only · new
filter by source
sharing classification
TLP describes sharing sensitivity, not copyright permission. Reader text is limited to source-provided descriptive material; original reporting stays with its publisher.