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 · 4,096 source documents · 4,064 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
LMSM: LLM Security Framework Inspired by Linux Security Modules
arXiv:2608.25697v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass them. Interpretability methods can expose model-internal signals along the generation path that could inform enforcement, but these signals are not security controls by themselves. Deployments that adapt them for safety typically couple each signal to its own calibration, policy logic, and intervention code, so ea…
An Analysis of the Impact of Psychological Factors and Techniques Across Different Types of Social Engineering
arXiv:2608.25670v1 Announce Type: new Abstract: Phishing is a well-known social engineering (SE) type used to trick individuals into revealing personal information or performing desired actions, like downloading and installing malware. Other SE types, like vishing and smishing, have emerged and are increasingly being used. As SE continues to successfully persuade victims into actions, the questions arise of which SE attack types are most effective for specific psychological f…
AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation
arXiv:2608.25667v1 Announce Type: new Abstract: The integration of Large Language Models (LLMs) into cybersecurity has transformed vulnerability assessment, but it has also produced a trustworthiness crisis driven by the unchecked proliferation of "AI slop." These artifacts, hallucinated vulnerabilities, plausible but incorrect patches, and semantically repackaged bug reports, impose a cognitive burden on human triage pipelines that mirrors a denial-of-service attack. This pa…
Defending the Peg: Real-Time Dynamic Protection and Anomaly Detection in DeFi Stablecoins
arXiv:2608.25600v1 Announce Type: new Abstract: With the rapid evolution of the Decentralized Finance (DeFi) ecosystem, stablecoins have emerged as a critical infrastructure bridging the cryptocurrency market with traditional financial paradigms. However, stablecoin systems rely heavily on smart contracts to execute automated operations. The immutable nature of these systems post-deployment means that the exploitation of security vulnerabilities can lead to irreversible, mass…
MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak Vulnerabilities
arXiv:2608.25490v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet how different factors shape their jailbreak vulnerabilities remains poorly understood. Existing benchmarks often couple harmful intent, prompt framing, visual semantics, and instruction carrier within individual jailbreak instances, obscuring the specific sources of observed vulnerabilities. To address this limitation, we introduce…
Separating Disclosure from Authorization: Field-Tier Minimization for Agent Action Mediation
arXiv:2608.25474v1 Announce Type: new Abstract: A system that authorizes an action must see enough of it to decide, and a system that attests to its decision must record enough to be audited. Both pressures push raw action parameters -- recipients, payment memos, record identifiers -- into an append-only ledger that cannot delete them. We show the two are separable. We classify each parameter field, not each action class, into three tiers: fields a policy may legitimately mat…
MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration
arXiv:2608.25457v1 Announce Type: new Abstract: Despite their strong ability to generate code, large language models often fail to produce secure code, as their outputs frequently contain security vulnerabilities. Secure code generation is inherently challenging because it requires solving a multi-objective problem: functional correctness and security. Existing approaches address this challenge by injecting external security knowledge or by using agentic feedback and iterativ…
Here is a GIFT: Enforcing User Data Isolation in LLM Serving via GPU Information Flow Tracking
arXiv:2608.25431v1 Announce Type: new Abstract: LLM serving frameworks process large volumes of user data--often containing sensitive information--on shared infrastructure. Ensuring isolation between users who share the same serving framework (on CPUs) and LLM operators (on GPUs) is critical for privacy protection. This paper presents GIFT, a GPU Information Flow Tracking system that enforces user data isolation in LLM serving with minimal overhead. Moreover, the design of GI…
LLMscope: Extracting LLM Assets from Edge AI Chips via Optical Probing
arXiv:2608.25321v1 Announce Type: new Abstract: The move of LLM inference to edge AI accelerators introduces new physical vulnerabilities. During execution, model parameters and intermediate inference states are repeatedly loaded into and processed on the chip, making them suscep- tible to physical side-channel attacks. In this work, by deploying laser voltage imaging, we show that one can extract LLM assets during inference, namely embeddings, attention, and quantized MLP we…
Automotive HSMs - Architectural Challenges and Security Implications
arXiv:2608.25216v1 Announce Type: new Abstract: Automotive electronic control units (ECUs) increasingly depend on hardware-rooted security to protect software integrity, authenticity, and lifecycle management in the presence of remote and physical threats. Hardware Security Modules (HSMs) have become a key building block in automotive system-on-chips (SoCs), providing isolated cryptographic services, secure key storage, and controlled execution under stringent real-time and c…
Authenticated Data Structures for Dynamic Workloads
arXiv:2608.25206v1 Announce Type: new Abstract: We introduce the Huffman-Merkle Tree (HMT), an authenticated data structure (ADS) for dynamic workloads where items may differ in access frequencies, and access frequencies can change over time. An ADS allows proving item membership against a short commitment to a large mutable state, with applications including verifiable storage, Internet transparency services, and blockchains. Optimizing ADS performance under continuously cha…
BGPay: An Incentive-Compatible Mechanism for BGP Hijack Filtering
arXiv:2608.25165v1 Announce Type: new Abstract: BGP hijacking remains a persistent threat as existing defenses, including RPKI/ROV suffer from a fundamental incentive misalignment: the networks best positioned to filter malicious announcements bear operational costs but receive no direct benefit, while the victim prefix owner captures all the value. We advocate a market-based alternative in which prefix owners post standing bounties for filtering invalid announcements of thei…
CA-less Mutual Co-Signing of Documents over a Unidirectional Visual Channel with Transported Hardware Attestation
arXiv:2608.25144v1 Announce Type: new Abstract: We describe and analyze a protocol for mutual co-signing of a document by two mobile devices that (i) communicate only over a one-way, lossy, low-bandwidth optical channel (an animated on-screen code read by the counterparty's camera), (ii) use no intermediary server on the trust path, and (iii) use no certificate authority. Trust in each party's public key is instead grounded in a hardware attestation token produced by the plat…
Static Detection of Post-Quantum Cryptographic Algorithms in Stripped Binaries for Digital Forensic Examination and Migration Assurance
arXiv:2608.25122v1 Announce Type: new Abstract: Currently, there is no method to verify from compiled binary code whether a quantum-vulnerable algorithm has been replaced by an approved post-quantum algorithm. Cryptographic discovery tools identify algorithms by symbols, library dependencies, and runtime behaviour; however, all these signals are destroyed by stripping, statically linking, and optimising a binary. This paper presents Kestrel, a static analysis method for ident…
Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation
arXiv:2608.24977v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances large language models by grounding outputs in external knowledge, improving factuality and reducing hallucinations. At the same time, the retrieval-augmented pipeline introduces new robustness and security risks, including corpus poisoning, backdoor attacks, privacy leakage, and fairness violations. Despite rapid progress in this area, existing surveys remain limited in their treatme…
ToolMinimize: Auditing and Rewriting LLM Agent Tool Calls to Minimize Privacy Exposure
arXiv:2608.24957v1 Announce Type: new Abstract: LLM agents routinely include privacy-sensitive data (PSD) in tool call arguments beyond what the invoked tools require, crossing trust boundaries to third-party services on every invocation. A controlled measurement on three production LLMs (GPT-4o, Claude 3.5 Sonnet, Llama-3.3-70B) shows that 81--88\% of tool calls include unnecessary PSD under default prompts; explicit privacy instructions still leave 36--76\% over-sharing. Ex…
[$] LWN.net Weekly Edition for August 27, 2026
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
When AI infrastructure becomes the target: Securing gateways and control points
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
FBI Disrupts China-Linked QTFY Infrastructure Used to Steal Data From U.S. Organizations
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
What Blockchain Data Tell Us About $457+ Billion in Potentially Taxable Crypto Activity
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Nimbus Manticore Expands Toolset With TWOSTROKE-Like Backdoor and SSH Tunneler
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
[$] An ongoing 3D-printer AGPL violation
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Armbian 26.8 released
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
NovaCookies Campaigns Abuse Genuine Docusign Notifications to Steal Microsoft 365 Sessions
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Security updates for Wednesday
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
CISA Red Team Compromised Two Critical Infrastructure Orgs, One Detected Nothing
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
LibreOffice 26.8 released
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Unpatched Kaltura mwEmbed Flaws Could Let Remote Attackers Read Files and Run Code
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Imagine the SOC Without a Queue: From Alert Backlog to AI Hypothesis Engine
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
VMs won't contain cyber-capable agents
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Claude Opus 4.6 Bypasses Gym Booking Limit, Cancels Other Users' Reservations in Tests
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Choose your fighter: Balancing competing requirements to select models for your AI SOC
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
OpenAI Bans Russian ChatGPT Accounts Used to Run Influence Operation
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
INTERPOL Operation Jackal IV Arrests 58, Identifies 263 in Global Cyber Fraud Crackdown
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
New SLEEPWALKER Backdoor Waits for One Crafted Packet, Then Runs Its Own Bytecode
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Critical Gitea RCE Actively Exploited as Reported Attack Drops Miner-Like Payload
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Fake Apple Support AI Calls Target Stolen-Device Owners for Passcodes and 2FA Codes
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Why Your AI Application Is Exposed Snyk
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Asynchronous Verifiable Information Dispersal with Low Space and Communication Complexity
arXiv:2608.24636v1 Announce Type: cross Abstract: The primary goal of a distributed storage system is to ensure that clients can both write and read data in a reliable and consistent manner, even in the presence of failures. While existing asynchronous verifiable information dispersal (AVID) protocols achieve optimal space complexity for storage and communication complexity for data retrieval in a Byzantine setting, the crucial operations of data dispersal and node recovery h…
Towards LLM-Enhanced Android Taint Analysis
arXiv:2608.24269v1 Announce Type: cross Abstract: Taint analysis is a fundamental technique for detecting sensitive data leaks in Android apps. However, traditional static tools, such as FlowDroid, still face well-known challenges due to the complexity of accurately modeling the Android framework. In this paper, we investigate whether off-the-shelf Large Language Models (LLMs) can effectively reason about taint flows in Android apps. Our preliminary approach relies on an agen…
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.