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
Bernard: GNOME Shell design dreams
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Thinking of ACE? We Can Do It with Fewer Tokens
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
New surveillance tech links your phone to your license plate
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
OpenAI Launches GPT-5.6-Cyber with Reduced Safeguards for Exploit Development
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Security updates for Tuesday
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Local governments in four states dealing with cyberattacks that have shut down services
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Kids’ online safety bill faces dim prospects of passage this session despite progress
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
A Malicious SIM Card Can Run Attacker Code Inside the Modems Behind Cellular IoT Devices
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Mozilla Revokes Firefox and Thunderbird Linux Signing Key After Key Lands in Private Repo
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Corma Raises $60 Million for Defensive Cybersecurity AI Model
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Researchers Built a Fake Crypto Startup and Hired Three Suspected North Korean IT Workers
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Here's why the new Pass-ta-key attack is mostly a nothingburger
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Extension Banned for Stealing AI Chats Returns to Chrome Store, Resumes Malicious Activities
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Researchers Turn USB Auto-Install Into a Full SYSTEM Takeover on Windows 11
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Kimwolf v7: An Evolution of the Kimwolf Botnet
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Hacker Conversations: Marcus Hutchins and the Journey From the Gray Zone to Redemption
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
OpenAI Unveils New Cybersecurity Model GPT-5.6-Cyber
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Gunra Ransomware Exploits Fortinet and Schneider Electric Flaws to Breach Networks
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Hackers Breach Polish Power Plant Controls via Private Cellular Network and Shut Turbine
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Mozilla Issues New Firefox GPG Key Following Exposure
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
BdThemes Supply Chain Attack Poisons JSON to Create Rogue WordPress Admins
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks
Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks arXiv:2608.09047v1 Announce Type: new Abstract: Backdoor attacks compromise training data so that a model retains clean accuracy but predicts an attacker-chosen target on triggered inputs. At very low poisoning rates, only a few samples convey the trigger--target association, making poison-sample selection critical. Existing methods typically rank candidates using per-samp…
Mind the Hook: Source-Level Auditing of Privacy Defenses in Retrieval-Augmented Generation
Mind the Hook: Source-Level Auditing of Privacy Defenses in Retrieval-Augmented Generation arXiv:2608.09001v1 Announce Type: new Abstract: Black-box privacy scores for retrieval-augmented generation (RAG) are difficult to interpret unless the audited defense's active pipeline hook is known. We propose an active-path audit: inventory source-level hooks over retrieval, retrieved content, and generation; map each metric to the leakage channel it observes; and validate generated…
A Complexity-Theoretic Approach to Proofs of Space
A Complexity-Theoretic Approach to Proofs of Space arXiv:2608.08993v1 Announce Type: new Abstract: A Proof of Space, PoS, as introduced by Dziembowski et al. [CRYPTO'15], is a two-phase protocol that enables a Prover to convince an efficient Verifier that it has allocated a large amount of persistent memory to storing some information. To our knowledge, all existing PoS protocols are only known to be secure in the random oracle model (or under ad hoc assumptions about crypto…
Beyond Best Response: Quantal Stackelberg Deception as Insurance Against Attacker Misspecification
Beyond Best Response: Quantal Stackelberg Deception as Insurance Against Attacker Misspecification arXiv:2608.08865v1 Announce Type: new Abstract: Stackelberg Security Games (SSG) assume that an attacker observes the defender's strategy and chooses the target that maximizes their expected utility perfectly. In most realistic applications this is not plausible, and in the case of cyber deception (e.g., using decoys) the purpose of the game is to induce uncertainty and mistake…
Treating Statewide CORS Networks as Spatially Distributed Sensors for GNSS Integrity Monitoring under Unintentional and Deliberate Threats
Treating Statewide CORS Networks as Spatially Distributed Sensors for GNSS Integrity Monitoring under Unintentional and Deliberate Threats arXiv:2608.08831v1 Announce Type: new Abstract: State departments of transportation (DOTs) in the United States increasingly rely on statewide continuously operating reference station (CORS) networks to support high-precision Global Navigation Satellite System (GNSS)-based positioning and timing for intelligent transportation systems. The…
Toward Metacognitive One-Shot Indirect Prompt Injection: Strategy Abstraction Via Outcome-Conditioned Reflection
Toward Metacognitive One-Shot Indirect Prompt Injection: Strategy Abstraction Via Outcome-Conditioned Reflection arXiv:2608.08795v1 Announce Type: new Abstract: Tool-using large language model (LLM) agents are vulnerable to indirect prompt injection (IPI), in which malicious instructions embedded in external observations manipulate subsequent agent decisions and actions. Most existing adaptive attacks rely on repeatedly querying and refining against the target agent, whereas…
HaloMark: A Spectral Threshold for Embedding-Vector Watermarking under C2PA
HaloMark: A Spectral Threshold for Embedding-Vector Watermarking under C2PA arXiv:2608.08645v1 Announce Type: new Abstract: Foundation-model embeddings are now a primary data asset, but the content-provenance machinery built for images and audio does not transfer to them. C2PA binds to an asset with a stable bit-level or perceptual identity; embeddings have neither, since quantisation, projection, fine-tuning, and windowed averaging reshape them in normal use and break any f…
Whose Refusal Is It? The Unmeasured Contribution of Black-Box Multimodal Guardrails
Whose Refusal Is It? The Unmeasured Contribution of Black-Box Multimodal Guardrails arXiv:2608.08641v1 Announce Type: new Abstract: A black-box guardrail is evaluated as though the safety number it earns were its own. It is not. A defended pipeline holds two components that can refuse (the guardrail, and the target model out of its own alignment), and every reported metric is a sum over both. We show that the guardrail's actual share of the safety credited to it runs from no…
SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills
SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills arXiv:2608.08468v1 Announce Type: new Abstract: Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security properties remain under-explored. We present \textsc{SkillsMetric}, a five-stage static analysis framework that scores skill packages along pattern density, statistical anomaly, dataflow taint, impor…
Differential Privacy for Markov Chain State Trajectories
Differential Privacy for Markov Chain State Trajectories arXiv:2608.08341v1 Announce Type: new Abstract: Data-driven systems may require state trajectories of Markov chains to function because these trajectories contain information that is useful to the system, e.g., a product's credit risk, a user's physical location, or a user's internet browsing behavior. However, sharing such state trajectories can reveal sensitive information about users, which presents a privacy threat…
Privacy-Preserving Data Drift Detection and Recovery for Large-Scale LLM Applications via Proxy Representations
Privacy-Preserving Data Drift Detection and Recovery for Large-Scale LLM Applications via Proxy Representations arXiv:2608.08245v1 Announce Type: new Abstract: LLM applications deployed at scale face a fundamental challenge: privacy constraints prevent direct inspection of user interactions, making it difficult to obtain any representative evaluation dataset or to track the ongoing evolution of production traffic. We present ProxyDrift, a framework that (i) identifies and me…
Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification
Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification arXiv:2608.08195v1 Announce Type: new Abstract: Large language models (LLMs) are high-value assets that can be derived through redeployment, fine-tuning, quantization, or further alignment. Because deployed LLMs are commonly exposed only through query APIs, ownership verification must often rely on black-box text responses. This setting is difficult: generations are open-ended and can vary across…
Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario
Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario arXiv:2608.08131v1 Announce Type: new Abstract: In the fictional Order 66, catastrophe does not arise from a powerful command alone: a trusted population is preconditioned, a short directive activates the concealed condition, and protective authority turns against the system. This paper translates that mechanism into an origin-neutral security analysis of tool-using large language …
Defending Retrieval-Augmented Intrusion Detection Against Knowledge Poisoning and Prompt Injection
Defending Retrieval-Augmented Intrusion Detection Against Knowledge Poisoning and Prompt Injection arXiv:2608.08100v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enables large language models to classify network flows and generate human-readable incident reports by retrieving semantically similar historical traffic from a vector knowledge base. However, the retrieval layer introduces vulnerabilities to knowledge poisoning and prompt-injection attacks. W…
Algebraic Attack on Convolutional Neural Networks with Max Pooling
Algebraic Attack on Convolutional Neural Networks with Max Pooling arXiv:2608.08030v1 Announce Type: new Abstract: Recovering the weights and biases of deep neural networks (DNNs) via black-box input-output queries, known as parameter extraction attacks, has been extensively studied for ReLU-based fully connected neural networks (FCNNs), but remains unexplored for convolutional neural networks (CNNs) with the max pooling function, a core architecture for computer vision and …
BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes
BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes arXiv:2608.08027v1 Announce Type: new Abstract: Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or external data. Existing detection methods only detect the presence of injection and refuse to respond upon detection, overlooking the fact that for many modern aligned …
A Blueprint for Collaborative Cybersecurity Operations Centres with Capacity for Shared Situational Awareness, Coordinated Response, and Joint Preparedness
A Blueprint for Collaborative Cybersecurity Operations Centres with Capacity for Shared Situational Awareness, Coordinated Response, and Joint Preparedness arXiv:2608.08011v1 Announce Type: new Abstract: With digital technologies now being part of the fabric of our societies, identifying and managing cybersecurity threats becomes imperative. Within the European Union, several initiatives are underway, aiming to motivate, regulate and eventually orchestrate the establishment …
EvoTrustRAG: Evolution-Aware Conflict Attribution and Evidence Handling for Reliable Retrieval-Augmented Generation
EvoTrustRAG: Evolution-Aware Conflict Attribution and Evidence Handling for Reliable Retrieval-Augmented Generation arXiv:2608.07933v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) improves the factuality of large language models with external knowledge, yet conflicting evidence remains a fundamental challenge in dynamic and adversarial environments. Existing approaches often treat conflicts as static inconsistencies and select more reliable knowledge, ov…
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.