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
0
Publisher text withheld
22
Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks
Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks arXiv:2608.05659v1 Announce Type: new Abstract: LLM customization platforms allow users to build task-specific models for code intelligence tasks by embedding instructions into system prompts, without modifying the underlying model parameters. While these platforms lower the barrier to developing customized LLMs, they also introduce a new attack surface: instruction backdoor attacks, …
Enhancing Anomaly Resilience in Research Networks: A Large-Scale Forecasting Benchmark for Dynamic Security Baselining
Enhancing Anomaly Resilience in Research Networks: A Large-Scale Forecasting Benchmark for Dynamic Security Baselining arXiv:2608.05605v1 Announce Type: new Abstract: Research and Education Networks (RENs) serve as critical infrastructure for scientific discovery, yet they face a unique security paradox: their normal traffic patterns which are characterized by massive, bursty "elephant flows" are statistically indistinguishable from volumetric attacks such as DDoS to convent…
Detecting Safety Training Modification in Language Models via Activation Analysis
Detecting Safety Training Modification in Language Models via Activation Analysis arXiv:2608.05578v1 Announce Type: new Abstract: We introduce AMS (Activation-based Model Scanner), a tool that detects modifications to safety training in language models by measuring the geometric structure of safety-relevant concepts in activation space. Safety training creates measurable separation between harmful and benign content classes; certain safety modifications collapse or rotate th…
When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems
When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems arXiv:2608.05563v1 Announce Type: new Abstract: Self-evolving skill (SES) systems distill agent trajectories into persistent skills, allowing untrusted experience to become trusted instruction. We introduce PoisonedEvolution, a trajectory-poisoning attack on this promotion process. Our skill-visible black-box attacker can inspect a target skill and contribute bounded evidence, but …
A Self-Explainable Deep Architecture for Security Applications
A Self-Explainable Deep Architecture for Security Applications arXiv:2608.05552v1 Announce Type: new Abstract: Deep learning models have become integral to security applications due to their ability to model complex relationships in data and detect sophisticated threats. However, their complexity makes it difficult to understand how predictions are generated, posing significant challenges for interpretability, particularly in security applications where transparency is criti…
Behavioral Residualization for Unsupervised Intrusion Detection in Automotive CAN Networks
Behavioral Residualization for Unsupervised Intrusion Detection in Automotive CAN Networks arXiv:2608.05548v1 Announce Type: new Abstract: Modern vehicles rely on the Controller Area Network (CAN) bus, whose design prioritizes low cost and real-time performance but provides no message authentication or encryption. An attacker with physical or remote access can therefore inject arbitrary frames, making intrusion detection an important defense-in-depth mechanism. Most publishe…
PromptShield Home: Ambient Multimodal Prompt Injection Defense for Smart-Home Agents
PromptShield Home: Ambient Multimodal Prompt Injection Defense for Smart-Home Agents arXiv:2608.05495v1 Announce Type: new Abstract: Smart-home assistants increasingly use multimodal large language models (MLLMs) that perceive video and audio directly. This raises a safety question specific to the home: can the agent tell a genuine user command from ambient or externally-sourced content, television speech, on-screen text, or an overheard conversation, that merely looks like …
Exploring Privacy Leakage and Data Disclosure Violations in the MacOS Application Ecosystem
Exploring Privacy Leakage and Data Disclosure Violations in the MacOS Application Ecosystem arXiv:2608.05474v1 Announce Type: new Abstract: The systematic and excessive data collection practices of tech companies have rendered online privacy both a necessity and a sought-after commodity. However, while the privacy risks of the web, mobile, and IoT ecosystems have been extensively examined, desktop environments have been largely overlooked. As desktop apps continue to be wide…
Quantifying Bitcoin Network Resilience Through Critical Scenario Discovery: A Dual-Layer Framework for Discovering Contentious Fork Conditions in Decentralized Consensus
Quantifying Bitcoin Network Resilience Through Critical Scenario Discovery: A Dual-Layer Framework for Discovering Contentious Fork Conditions in Decentralized Consensus arXiv:2608.05461v1 Announce Type: new Abstract: Bitcoin's consensus depends not only on protocol rules but on the emergent behavior of a heterogeneous network of nodes with divergent economic stakes. Whether a contentious soft fork resolves cleanly or fractures into a persistent chain split is difficult to p…
Robust Context-Aware Detection of Malicious Instructions in Text
Robust Context-Aware Detection of Malicious Instructions in Text arXiv:2608.05430v1 Announce Type: new Abstract: The remarkable instruction-following ability of modern LLMs has enabled their practical use as the minds of agents that can autonomously complete increasingly complex tasks. Therein, however, also lies their vulnerability to attacks which embed malicious instructions in text, common variants of which are known as indirect prompt injection (IPI). A fundamental task…
S12X Patch Diffing with QBinDiff
S12X Patch Diffing with QBinDiff arXiv:2608.05350v1 Announce Type: new Abstract: This paper presents a reverse engineering analysis of a firmware update for a commercial vehicle Brake ECU. We analyze the updater executable to extract firmware and perform differential binary analysis of the S12X architecture firmware images. Our research identifies specific changes in the recall that address undocumented vulnerabilities in legacy protocol processing. We demonstrate that the p…
The Trust-Free Aggregation Layer of the Unicity Infrastructure
The Trust-Free Aggregation Layer of the Unicity Infrastructure arXiv:2608.05316v1 Announce Type: new Abstract: Unicity is a novel blockchain infrastructure for enabling users to execute off-chain peer-to-peer token transactions while preventing parallel states of tokens (double-spending) with minimal blockchain complexity and storage. A key component of the infrastructure is the Aggregation Layer responsible for storing information about the spent states of tokens and provid…
eMicro: Real-Time Multi-Hop Access Control for Microservices with eBPF
eMicro: Real-Time Multi-Hop Access Control for Microservices with eBPF arXiv:2608.05300v1 Announce Type: new Abstract: Modern cloud applications often comprise thousands of microservices whose interactions form complex request paths. Traditional inter-service access control restricts individual service-to-service requests, but fails to prevent multi-hop attacks, where each hop appears legitimate yet the overall path violates security intent. This gap leaves systems exposed t…
The Hidden Life of Public Safety Communications Signals: A Comparative Security Analysis of TETRA, TETRAPOL, and P25
The Hidden Life of Public Safety Communications Signals: A Comparative Security Analysis of TETRA, TETRAPOL, and P25 arXiv:2608.05247v1 Announce Type: new Abstract: Public-safety agencies and critical infrastructure operators rely on trunked land-mobile radio (LMR) systems, based on P25, TETRA, and TETRAPOL. These systems are expected to protect not just the content of a communication but the fact of it. Yet LMR standards leave a stark gap between confidentiality of \emph{co…
CyberBridge: Bridging the Gap Between Cybersecurity Education and Industry
CyberBridge: Bridging the Gap Between Cybersecurity Education and Industry arXiv:2608.05231v1 Announce Type: new Abstract: This full research paper presents CyberBridge, a framework that automatically maps cybersecurity job descrip- tions to professional role profiles. As the cybersecurity landscape evolves rapidly, it is difficult for academic programs to align curricula with the competencies expected in practice. CyberBridge addresses this gap by decomposing a given vacanc…
A Survey of Adversarial Efficiency Degradation for Vision Transformer by Exploiting Input-adaptive Optimization
A Survey of Adversarial Efficiency Degradation for Vision Transformer by Exploiting Input-adaptive Optimization arXiv:2608.05217v1 Announce Type: new Abstract: Vision Transformers (ViTs) increasingly rely on input-adaptive inference, such as token pruning and early halting, to meet energy and latency budgets. This survey examines a recent class of adversarial efficiency degradation attacks that target these mechanisms to increase computation without necessarily degrading acc…
ASTELD: A Six-Axis Classification Framework for Autonomous AI Agents - Design, Evaluation, and an OpenClaw Case Study
ASTELD: A Six-Axis Classification Framework for Autonomous AI Agents - Design, Evaluation, and an OpenClaw Case Study arXiv:2608.05201v1 Announce Type: new Abstract: Autonomous AI agent platforms differ substantially in architecture, security, tool integration, execution, autonomy, and deployment, yet the field lacks a common classification scheme for comparing these design choices. We propose ASTELD, an operational six-axis classification framework for autonomous AI agents:…
Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents
Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents arXiv:2608.05199v1 Announce Type: new Abstract: Autonomous security agents operate as staged pipelines, such as classifying network traffic and then attributing attacks to a specific technique. Split conformal prediction gives each stage finite-sample coverage, but deployment requires a trajectory-level guarantee across the full chain. These guarantees do not compose automatically when stages are in…
ChainDrop: Inside a Self-Propagating npm Worm
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
When Agentic Glue Melts: Exploiting Cloudflare Code Mode and Workers
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Six stable kernels with a security fix
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Why metaphor may dictate your security strategy
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
New Zapscape KVM Flaw Could Let Privileged L1 Guest Code Escape to Linux Hosts
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Day 2 at Black Hat: Check Point Research Takes the Stage
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Cyberattack on North Carolina Ports ‘contained’ as Coast Guard, state officials investigate
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Cisco Patches 12 SD-WAN and IOS XE Flaws, Including Three 9.8 CVSS Score Bugs
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Canadian Man Pleads Guilty in Snowflake Extortions
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
New Interrupt Injection Attack Can Bypass Spectre v2 Defenses on Intel and AMD CPUs
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
ThreatsDay: Odysseus RCE, Samsung One-Click Takeover, iCloud Backdoor Fight + 27 More Stories
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Snowflake Hacker Pleads Guilty in US Court
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Penlink Plugs Into Trusted Blockchain Data With Chainalysis
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
UNC6671 Rebrands: Multi-Brand Vishing Extortion Targets Financial Services and Enterprise Cloud Environments
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
[$] Bringing BPF to binfmt_misc
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Rust Coreutils 0.10 released
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Belarusian cybercriminal behind Ransom Cartel gets 16-year prison sentence
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Security updates for Thursday
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Over 4,400 Rockwell PLCs Exposed Online, 22 Found in Water Attack Cities
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Estimated $30 Million Stolen in Violent Crypto Attacks in 2026 as France Records Emerges as Hotspot
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Podcast: Compliance Won’t Save You: The Future of Cyber Risk with Edna Conway
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
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.