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
17
The Network Has Become the Control Plane for AI Security
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Semiconductor Firm Analog Devices Discloses Data Breach
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Building secure Uniswap v4 hooks
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Hackers Exploit AnySign4PC via Hacked Korean Sites to Install Backdoors Without Prompts
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
SilverFox Targets Japanese Manufacturer with 3-Driver BYOVD Chain and ValleyRAT
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Chinese-Speaking Threat Actor Harnesses AI Models for Autonomous Cyberattacks
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Black Hat special: Rewind and revisit
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Critical Ruflo Flaw Lets Attackers Spawn Rogue AI Swarms
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
1 in 5 Data Center Assets Are Within Easy Reach of Attackers
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Beyond the screenshot: Why you should verify what you see
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
US and Allies Update SBOM Guidance
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Chrome 151 Patches 370 Vulnerabilities
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Russian Hackers Exploit Microsoft OWA Flaw to Keep Mailbox Access After Credential Rotation
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
FCC Blocks New Foreign-Produced Robots and Power Inverters Over Cyber Risks
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Cisco Secure FMC Zero-Day Exploited in the Wild
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Amazon Links Debug and Chalk npm Hijack to North Korea’s Sapphire Sleet
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Cisco FMC Zero-Day Actively Exploited, Static Credentials Could Expose Sensitive Data
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents
AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents arXiv:2607.26998v1 Announce Type: new Abstract: Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools. This dependence allows defenders to inject deceptive observations that can mislead the agent's decision-making process. However, existing defenses rely heavily on static, isolated artifacts pla…
InkShield: Writing Style Protection Against Unauthorized Handwriting Mimicry
InkShield: Writing Style Protection Against Unauthorized Handwriting Mimicry arXiv:2607.26976v1 Announce Type: new Abstract: Recent handwritten text generators can reproduce a writer's style from publicly available references, posing risks of document forgery and identity misuse. An attacker may use a publicly available handwritten note or signature sample to generate forged recommendation letters or authorization forms, leading to document fraud, identity misuse, and mislea…
Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning
Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning arXiv:2607.26933v1 Announce Type: new Abstract: Federated Learning (FL) is vulnerable to backdoor attacks because of its distributed nature in edge computing scenarios. Existing defense methods show limited efficacy as they overlook the deviations among benign local updates caused by statistical heterogeneity and the stealthiness of backdoor attacks. To tackle these issues, we p…
ToxScreen: Detecting Whether an LLM Has Been Poisoned
ToxScreen: Detecting Whether an LLM Has Been Poisoned arXiv:2607.26849v1 Announce Type: new Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no trai…
Before Agents Speak: Pre-hoc Failure Risk Inference in Multi-Agent Systems
Before Agents Speak: Pre-hoc Failure Risk Inference in Multi-Agent Systems arXiv:2607.26836v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) have exhibited remarkable capabilities in collaborative reasoning and decision-making, yet their interconnected communications introduce new systemic risk: localized hallucinations can propagate along agent communication chain, amplify through interactions, and ultimately trigger cascading failures. Existing countermea…
SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response
SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response arXiv:2607.26791v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities. However, existing cybersecurity benchmarks focus on pre-compromise settings where agents are placed in a clean and idea…
Verifiable Random Sampling
Verifiable Random Sampling arXiv:2607.26734v1 Announce Type: new Abstract: Verifiable random functions (VRF) underpin a wide range of applications that require publicly verifiable evaluations of a pseudorandom function on a given input. However, once the public key is published, the induced function is fixed and is a deterministic function of the input. This determinism can enable collusion and grinding-style attacks in which adversaries precompute and selectively exploit fa…
FARI: Robust One-Step Inversion for Watermarking in Diffusion Models
FARI: Robust One-Step Inversion for Watermarking in Diffusion Models arXiv:2607.26723v1 Announce Type: new Abstract: Inversion-based watermarking is a promising approach to authenticate diffusion-generated images, yet practical use is bottlenecked by inversion that is both slow and error-prone. While the primary challenge in the watermarking setting is robustness against external distortions, existing approaches over-optimize internal truncation error, and because that error…
Not In My Git Yard: Catching Backdoors at Commit and Release Time
Not In My Git Yard: Catching Backdoors at Commit and Release Time arXiv:2607.26719v1 Announce Type: new Abstract: Code-level backdoors-stealthy code changes that grant hidden privileges via secret triggers-pose a persistent threat to opensource software. Known attempts to inject such backdoors into widely used projects through malicious commits, tampered release packages, or compromised third-party dependencies, were stopped only by luck and manual review. Existing Continuou…
Graph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability Detection
Graph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability Detection arXiv:2607.26656v1 Announce Type: new Abstract: Real-world vulnerabilities often span multiple functions, yet most learning-based detectors classify each function in isolation: on a sample of real CVEs, we find that 71.7% of vulnerable functions require evidence from outside the function to be classified correctly. Agentic reinforcement learning (RL) could close this gap by enab…
Fingerprint-Driven Automation: Coupling Reconnaissance with POC Verification
Fingerprint-Driven Automation: Coupling Reconnaissance with POC Verification arXiv:2607.26655v1 Announce Type: new Abstract: In the field of network security confrontation, reconnaissance is the first and most critical step. Accurate, efficient, and comprehensive reconnaissance can help network security workers more fully understand the target's current state, identify potential weaknesses, and formulate a targeted attack strategy. However, there are some problems in the exi…
Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses
Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses arXiv:2607.26639v1 Announce Type: new Abstract: A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% defense success rate. We show it can be breached by composing two attacks that are individually harmless against it: an established code-completion encoding and an established best-of-N searc…
Guarding Organizations Against Malware Risk: A Novel Graph-Based Malware Detection Method
Guarding Organizations Against Malware Risk: A Novel Graph-Based Malware Detection Method arXiv:2607.26634v1 Announce Type: new Abstract: Organizational digitalization expands cybersecurity risks, making cybersecurity an increasingly important research area in Information Systems (IS). Among these risks, malware has become a pervasive and destructive threat. Byte-based machine learning (ML) methods are widely used for malware detection but remain vulnerable to evasive behavi…
CDN Tsunami: Exploiting HTTP/3-HTTP/1.1 Conversion for DoS Attacks
CDN Tsunami: Exploiting HTTP/3-HTTP/1.1 Conversion for DoS Attacks arXiv:2607.26589v1 Announce Type: new Abstract: Content Delivery Networks (CDNs) provide high availability, accelerate content delivery for their host websites, but are also vulnerable to different types of Denial-of-Service (DoS) attacks. Prior works have studied a variety of DoS attacks with HTTP/1.1 or HTTP/2 connections, but most of them are being fixed, making CDNs robust against such attacks. One unexpl…
Recover, Decode, Reguard: Guard-Agnostic Defense Amplification againstEncoded VLM Jailbreaks
Recover, Decode, Reguard: Guard-Agnostic Defense Amplification againstEncoded VLM Jailbreaks arXiv:2607.26574v1 Announce Type: new Abstract: Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet they judge an input's surface form, not its meaning: a harmful request re-encoded as set theory, formal logic, a rare language, code, or an image of text slips past a guard that would block it in plain language -- the decode gap. The natural…
QUIC-TRIP: A Triple-Redundant Journey Toward Secure Substation Communications
QUIC-TRIP: A Triple-Redundant Journey Toward Secure Substation Communications arXiv:2607.26379v1 Announce Type: new Abstract: Modern power systems rely on real-time substation communication protocols, such as the Routable Generic Object-Oriented Substation Event (R-GOOSE), for critical control and protection functions. However, these protocols often lack built-in security features and prioritize availability over confidentiality and integrity, making them susceptible to fals…
A Controlled Candidate-Set Benchmark for Offline Satellite-Security Plan Decomposition
A Controlled Candidate-Set Benchmark for Offline Satellite-Security Plan Decomposition arXiv:2607.26371v1 Announce Type: new Abstract: Some security-development settings require local models that map an objective to an ordered, checkable plan. We present a low-rank decomposition adapter and release a case-disjoint corpus with 24 authored decompositions and 83 derived next-step examples across 24 satellite-security cases. To prevent reference-plan leakage, prompts contain one…
StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents
StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents arXiv:2607.26314v1 Announce Type: new Abstract: Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisticated operators from detectable ones. Elite security researchers and advanced persistent threats achieve their objectives unnoticed; autonomous agents increasingly inherit the same offensive tasks,…
Learning the Word Problem: Geodesic Lengths and Cryptographic Applications
Learning the Word Problem: Geodesic Lengths and Cryptographic Applications arXiv:2607.26241v1 Announce Type: new Abstract: The Word Problem has been a subject of intensive mathematical study for over a century, initially driving advances in combinatorial group theory and more recently emerging as a foundational hardness assumption in post-quantum cryptography (PQC). While generally undecidable, several families of infinite non-abelian groups exhibit solvable or algorithmical…
On Exercising Governance Power in Decentralized Autonomous Organizations
On Exercising Governance Power in Decentralized Autonomous Organizations arXiv:2607.26204v1 Announce Type: new Abstract: A decentralized autonomous organization (DAO) is a governance entity that allows its stakeholders to manage blockchain-based protocols through smart contracts. The DAO explicitly specifies how stakeholders make and enforce decisions concerning a protocol's operation in a smart contract, aptly referred to as its governance contract. The design of this gover…
(EC)2: Event-Centric Explainability for Cybersecurity Through Multi-Agent LLM Investigations
(EC)2: Event-Centric Explainability for Cybersecurity Through Multi-Agent LLM Investigations arXiv:2607.26201v1 Announce Type: new Abstract: Security operations centers rely on anomaly detection systems to flag suspicious events. Feature-level explanations for anomaly detectors offer limited value for operational investigations. To effectively handle alerts, analysts need to know contextual relationships and need actionable understanding of the entities involved. This paper …
GPT-Red: Automated Red Teaming via Self-Play at Scale
GPT-Red: Automated Red Teaming via Self-Play at Scale arXiv:2607.26115v1 Announce Type: new Abstract: We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs. The goal of this model is to evaluate and improve the robustness of our production systems. To this end, we use it to adversarially train GPT-5.6, our most robust model to prompt injections to date. To create GPT-Red, we design a sca…
A Reference-Free Score for Detecting Silent Reasoning Failures in Large Language Models
A Reference-Free Score for Detecting Silent Reasoning Failures in Large Language Models arXiv:2607.26102v1 Announce Type: new Abstract: Mathematical chain of thought (CoT) evaluation is commonly reduced to whether the final answer matches a reference. This conflates producing a correct conclusion with producing a valid derivation an invalid chain can accidentally reach the right answer, while a valid calculation can be followed by a transcription error. We call this mismatch…
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.