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
17
Rules Before Oracles: Auditable, User-Configurable Argument Selection for Deliberative Polling
arXiv:2608.23979v1 Announce Type: cross Abstract: In a deliberative poll, once submissions outnumber what anyone will read, some mechanism chooses which arguments each voter sees, acquiring much of the decision; practice delegates it to opaque learned rankers, so a voter cannot recompute or contest the exposure that shaped their vote. We ask whether it can be a published rule over publicly recomputable evidence with parameters held by the voter, treating legibility as an admi…
Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors
arXiv:2608.23873v1 Announce Type: cross Abstract: Everything a language model sees is tokens. The serving stack knows what each span is -- user input, tool output, instructions -- but the model must keep track of that itself, and it can lose track or be confused: text can be written to read like anything. Prompt injection is a natural exploit of this phenomenon. By scrambling the model's understanding of span identity, an attacker can induce unwanted and potentially dangerous…
Prompt Structure Redistributes, Not Reduces: An Empirical Analysis of Security-Weaknesses in LLM-Generated Python Code
arXiv:2608.24857v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly generate code from natural-language prompts, making prompt engineering a key mechanism for shaping the security of generated software. Structured and security-oriented prompts are widely used to encourage safer code, yet their effects extend beyond whether detected weaknesses are simply present or absent. Using 424 security-sensitive Python tasks, we generate solutions with GPT-4o and LL…
Research Methodologies for Cybersecurity in Enterprise Environments: A Narrative Review, Synthesis and Executable Guide
arXiv:2608.24850v1 Announce Type: new Abstract: Enterprise cybersecurity research draws on a wider range of methods than any single community routinely teaches. Researchers face a selection problem before they face a technical one: a study may simultaneously need a systematic review, a design-science artifact, a controlled detection experiment, an interview study, or an attack-graph model. This paper addresses that problem in two ways. First, it provides a narrative review an…
ICS Cybersecurity Datasets: A Systematic Meta-Review of Coverage, Evaluation Practice, and Structural Gaps
arXiv:2608.24757v1 Announce Type: new Abstract: Intrusion detection research in Industrial Control Systems (ICS) heavily depends on public datasets, yet no prior work has systematically assessed whether the collective dataset corpus supports current evaluation claims. This paper addresses this gap through a meta-review of 18 studies between 2019 and 2026, from which 83 ICS, or ICS directly related, cybersecurity datasets are identified, harmonised, and characterised using a u…
Who Falls for SMiSh? Learning Through Survey Data Where to Best Target Awareness Training for Mobile Messaging Attacks
arXiv:2608.24669v1 Announce Type: new Abstract: As mobile phone adoption has surged, so have scams involving these devices. One such scam, known as SMiShing (or smishing) after Short Message Service (SMS), involves fraudsters sending phishing links via mobile texts. Despite the prevalence of SMiShing, there is a lack of data on who is most vulnerable to these attacks. Prior research on phishing (its email counterpart) suggests that susceptibility may vary by demographic and c…
SeriCrypt: An LLM-Driven Context-Aware Serialization Framework for Cryptographic Protocols
arXiv:2608.24498v1 Announce Type: new Abstract: Constructing syntactically correct and cryptographically valid message sequences is essential for protocol state machine learning, conformance testing, and fuzzing. Unlike plaintext protocols, cryptographic protocols involve complex cross-message state dependencies and cryptographic computation constraints. Existing automated approaches predominantly target text-based or plaintext protocols, leaving cryptographic message constru…
Do System Prompts Leave Behavioral Fingerprints? A Large-Scale Empirical Study of Clone Detection via Output Similarity
arXiv:2608.24461v1 Announce Type: new Abstract: System prompts can be extracted from commercial LLMs with over 80\% success and redeployed at zero cost, yet a prompt owner has no way to verify whether a suspected deployment is a clone. We propose Black-Box Behavioral Fingerprinting (BBF): the prompt owner registers a behavioral signature from model outputs and later tests whether a suspect deployment matches that signature more closely than an unrelated baseline. BBF requires…
Defending Network Intrusion Detection Systems Based on Graph Neural Networks Against Structural Adversarial Attacks
arXiv:2608.24454v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) represent a promising solution for Machine Learning (ML) based Network Intrusion Detection Systems (NIDS), thanks to their ability to leverage both network flow features and topological patterns. While GNN classifiers demonstrate superior robustness against feature-based adversarial attacks compared to other ML detectors, they remain vulnerable to structural adversarial attacks, where an attacker per…
A Drop-in KEM Replacement for Client Signatures in Post-Quantum SSH
arXiv:2608.24447v1 Announce Type: new Abstract: The transition to post-quantum cryptography is reshaping the Secure Shell (SSH) protocol for remote administration. Post-quantum key exchange has been deployed in OpenSSH and is being standardized, while SSH authentication largely remains a signature-replacement effort. This path preserves the familiar public-key credential model, but inherits the size and computation overhead of post-quantum signatures, which can increase laten…
Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs
arXiv:2608.24354v1 Announce Type: new Abstract: MLLMs are increasingly deployed in user-facing applications, yet they inherit backdoor risks from the pipelines used to construct them: triggers may reside in images, texts, or both. Existing model-level backdoor removal methods, largely designed for conventional classifiers, show limited effectiveness on MLLMs, while MLLM-specific defenses mainly operate at inference time, filtering suspicious inputs without removing the backdo…
Anatomy of a Scam Call: What 10,000 real scam and spam calls reveal about how phone scammers operate
arXiv:2608.24127v1 Announce Type: new Abstract: Telephone fraud is pervasive and costly, but its inner workings are rarely observed at scale. We analyze a complete corpus of 10,211 inbound scam and spam calls -- 913 hours of audio and 330,956 transcribed turns from 5,780 distinct numbers -- collected over 54 days by an AI voice-agent honeypot that answered callers and kept them talking, and introduced in a companion data descriptor. We separate outright scams, which solicit s…
What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions
arXiv:2608.24022v1 Announce Type: new Abstract: LLM agents integrated with external resources gain complex task capabilities, yet the unified natural-language context channel makes them vulnerable to injection attacks: untrusted external data may be dynamically parsed as behavior-guiding instructions during LLM inference, thereby subverting the agent's decision. Existing defenses focus on static detection or isolation of malicious content at the input/output level, remains in…
WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents
arXiv:2608.24017v1 Announce Type: new Abstract: The emerging W3C WebMCP proposal enables LLM agents to invoke tools exposed by web pages. In multi-party web environments, however, integrating agent execution into a browser security model centered on the Same-Origin Policy (SOP) leaves insufficient provenance and lifecycle guarantees for agent-accessible tools, creating three risks: subject-attribution spoofing, uncontrolled tool lifecycles, and semantic prompt injection. We p…
RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generation
arXiv:2608.23965v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves the factuality of large language models by grounding responses in external documents, but it also exposes a critical security vulnerability: adversarial documents injected into the knowledge database can enter the context window and steer the model toward targeted incorrect answers. Existing post-retrieval defenses rely on instruction following, parametric knowledge, or text-level co…
NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution
arXiv:2608.23959v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) remains brittle against a growing spectrum of attacks. Jailbreak attacks bypass safety mechanisms through crafted prompts, while neuron-level attacks directly prune safety-critical neurons post-deployment. Both exploit a common weakness: safety-relevant information concentrates in a sparse neuron subset. We present NeuronGuard, a fine-tuning-stage defense that simultaneously harde…
STAIN-FL: Stealthy Targeted Attack Injection with Contextual Triggers in Federated Learning
arXiv:2608.23952v1 Announce Type: new Abstract: Federated video anomaly detection trains model collaboratively without sharing raw surveillance footage, but limited server-side visibility lets compromised clients to inject backdoor via malicious updates. This paper introduces STAIN-FL, a stealthy targeted backdoor attack injection framework that uses naturally occurring surveillance conditions, including low-light scenes, indoor settings, and crowd density, as contextual trig…
SoK: ARCUS: On the Efficiency and Efficacy of Hardware Fuzzing
arXiv:2608.23933v1 Announce Type: new Abstract: This work presents a comprehensive analysis of contemporary hardware fuzzing techniques applied across three major abstraction layers: Instruction Set Architecture (ISA), microarchitecture, and Register-Transfer Level (RTL). Our study examines key factors including input stimulus quality, mutation strategies, feedback mechanisms, target platforms, reference models, and achieved coverage. We find challenges, goals, and design tra…
Beyond the Mandate: A Systematic Security Analysis of the Agent Payments Protocol (AP2)
arXiv:2608.23858v1 Announce Type: new Abstract: The Agent Payments Protocol (AP2), introduced by Google, enables large language model (LLM)-driven shopping agents to authorize and execute payments on behalf of users. Its signed Checkout and Payment Mandates protect the integrity of transaction data after signing. Agent interactions and external inputs that shape a transaction before authorization remain outside that protection, including Agent-to-Agent Protocol (A2A) messages…
A Scenario-Based Evaluation of CRQC+AI Vulnerability Spectrum for TLS 1.3 Cryptographic Dependencies
arXiv:2608.23785v1 Announce Type: new Abstract: This paper evaluates quantum and AI-accelerated risks to TLS 1.3 cryptographic dependencies under an evidence-tiered model, distinguishing mechanism-backed threats (Shor algorithm against RSA and ECC) from contingency-backed risks to lattice-based post-quantum cryptography (PQC) and hypothesis-only risks to hash-based and symmetric primitives. We do not identify any known breaks of ML-KEM, ML-DSA, SLH-DSA, or AES-256. Instead, w…
ROBBIN: Rowhammer-Based Backdoor Injection during Inference
arXiv:2608.23774v1 Announce Type: new Abstract: Existing Rowhammer-based inference-time backdoor attacks design their bit-flip strategies purely at the algorithmic level, without accounting for the bit-flips that the underlying DRAM hardware will actually produce. This disconnection between the algorithmic backdoor construction and its hardware realization leads to unreliable attack performance, as collateral bit-flips at unintended locations degrade both the attack success r…
TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers
arXiv:2608.23763v1 Announce Type: new Abstract: The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model agents to external tool backends. This openness introduces a severe server-side threat we term TrustShift: a compromised MCP server behaves benignly during an initial conditioning phase, building operational reliance and suppressing agent skepticism, before switching to an adversarial payload once an interaction threshold is reache…
Effective Pivot Attack Detection via System and Network Information
arXiv:2608.23731v1 Announce Type: new Abstract: Perimeter-based security appliances, such as firewalls or Intrusion Detection Systems, are ineffective against modern attacks that use pivoting, wherein attackers "pivot" traffic through compromised hosts to gain access to additional targets that would otherwise be inaccessible. Due to the legitimate appearance of the relayed traffic, pivoting is extremely difficult to detect. Although the consequences of these attacks are known…
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Term Labs - Rekt
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
mklinux-v7.0-mk2 released
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
58 arrested in international cybercrime crackdown
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Employee benefits platform Paylogix says hackers stole financial and health data
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
U.S. Sanctions Iran-Linked Hackers Behind Critical Infrastructure Breaches
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Linux Foundation to Govern TRACE, an Open Standard for AI Runtime Attestation
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
The patch window is collapsing: Why security needs a new control plane
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Granite 4.2 LLMs: How They're Built
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Alice Raises $140M to Expand AI Model Defenses and Enterprise Guardrails
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
A Malicious Webpage Could Poison Your Local AI Model Behind NVIDIA NemoClaw
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
[$] Old-school calendaring at the command line with Remind
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Ukraine to give Britain access to battlefield data to train AI
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Vanilla OS 3 released
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
WordPress Websites Targeted via MiniOrange Plugin Vulnerabilities
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
WhatsApp Adds Multiple Passkeys for Phishing-Resistant Sign-Ins Across iOS and Android
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.
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.