REPORTS
Fresh threat intelligence we ingest from public vendor and research feeds — each report linked to its original source. Search, filter by source, and open the reference.
Reports
Newest first. Search, filter by source, open the original.
850 reports · page 20 of 22
arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
Analyzing Codes of Conduct for Online Safety in Video Games at Scale arXiv:2605.15047v1 Announce Type: new Abstract: Online video games have become major online social spaces where users interact, compete, and create together. These spaces, however, expose users to a wide spectrum of online harms, including harassment, discrimination, inappropriate content, privacy breach, cheating, and more. The shape and severity of such harms vary across game design, mechanics, and commun…
Read original ↗https://arxiv.org/abs/2605.15047arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models arXiv:2605.14514v1 Announce Type: new Abstract: Large Language Models (LLMs) deployed in high-stakes applications must simultaneously manage multiple risks, yet existing defenses are almost exclusively evaluated in isolation under a one-shot deployment assumption. In practice, providers patch models incrementally throughout their lifecycle-responding to newly exposed vulnerabilities or targ…
arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
Exploiting LLM Agent Supply Chains via Payload-less Skills arXiv:2605.14460v1 Announce Type: new Abstract: Autonomous agents powered by Large Language Models (LLMs) acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for systematic security evaluation. Current auditing mechanisms are effective at identifying explicit code payloads and predefined threat …
Read original ↗https://arxiv.org/abs/2605.14460arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
MemLineage: Lineage-Guided Enforcement for LLM Agent Memory arXiv:2605.14421v1 Announce Type: new Abstract: We introduce MemLineage, a defense for LLM agent memory that attaches both cryptographic provenance and LLM-mediated derivation lineage to every entry. Recent and concurrent work shows that untrusted content can be written into persistent agent state and re-enter later sessions as an instruction; the remaining systems question is how to preserve useful memory recall wh…
Read original ↗https://arxiv.org/abs/2605.14421arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
The Great Pretender: A Stochasticity Problem in LLM Jailbreak arXiv:2605.14418v1 Announce Type: new Abstract: "Oh-Oh, yes, I'm the great pretender. Pretending that I'm doing well. My need is such, I pretend too much..." summarizes the state in the area of jailbreak creation and evaluation. You find this method to generate adversarial attacks proposed by a reputable institution (e.g., BoN from Anthropic or Crescendo from Microsoft Research). However, this method does not deli…
Read original ↗https://arxiv.org/abs/2605.14418arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
Model Forensics in AI-Native Wireless Networks: Taxonomy, Applications, and Case Study arXiv:2605.14387v1 Announce Type: new Abstract: As artificial intelligence (AI) is increasingly embedded in wireless networks, models are becoming core components that influence signal processing, resource scheduling and network control. However, model anomalies, tampering and malicious functions also introduce new security risks. In this article, we focus on model forensics in AI-native w…
Read original ↗https://arxiv.org/abs/2605.14387arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model arXiv:2605.14291v1 Announce Type: new Abstract: The rapid advancement of Large Vision-Language Models (LVLMs) is increasingly accompanied by unauthorized scraping and training on multimodal web data, posing severe copyright and privacy risks to data owners. Existing countermeasures, such as machine unlearning and watermarks, are inherent post-hoc approaches that ac…
Read original ↗https://arxiv.org/abs/2605.14291arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
Web Agents Should Adopt the Plan-Then-Execute Paradigm arXiv:2605.14290v1 Announce Type: new Abstract: ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default for web agents. Instead, web agents should default to plan-then-execute: commit to a task-specific program before observing runtime web content, then execute it. The reason is that web content mixes inputs from many parties. A…
Read original ↗https://arxiv.org/abs/2605.14290arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
On the (non-)resilience of encrypted controllers to covert attacks arXiv:2605.14230v1 Announce Type: new Abstract: The security of networked control systems (NCS) is receiving increasing attention from both cyber-security and system-theoretic perspectives. The former focuses on classical IT security goals such as confidentiality, integrity, and availability of process data, while the latter investigates tailored attacks (and detection schemes), including covert and zero-dyna…
Read original ↗https://arxiv.org/abs/2605.14230arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
Characterizing AI-Assisted Bot Traffic in Darknet Data: Implications for ICS and IIoT Security arXiv:2605.14209v1 Announce Type: new Abstract: The rise of automated scanning tools and AI assisted reconnaissance agents has significantly altered internet background traffic patterns, threatening the baseline assumptions underlying intrusion detection systems (IDS) deployed in critical infrastructure networks. This paper characterizes the evolution of automated bot traffic by an…
Read original ↗https://arxiv.org/abs/2605.14209arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
DSTAN-Med: Dual-Channel Spatiotemporal Attention with Physiological Plausibility Filtering for False Data Injection Attack Detection in IoT-Based Medical Devices arXiv:2605.14165v1 Announce Type: new Abstract: False data injection (FDI) attacks on Internet of Medical Things (IoMT) sensor streams falsify vital signs in transit, threatening patient safety and defeating clinical monitoring systems that lack cyber-physical anomaly detection capability. Existing deep learning det…
Read original ↗https://arxiv.org/abs/2605.14165arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents arXiv:2605.14153v1 Announce Type: new Abstract: Exploitation is not a binary event. It is a ladder of acquiring progressive capabilities, from executing a single buggy line of code to taking full control of the target. However, existing LLM security benchmarks treat a crash as exploitation success. That single binary outcome collapses the hard parts of exploitation: the transition from triggering a bug …
Read original ↗https://arxiv.org/abs/2605.14153arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
Memory Forensics Techniques for Automated Detection and Analysis of Go Malware arXiv:2605.14020v1 Announce Type: new Abstract: The Go programming language has become increasingly popular among malware developers due to its ability to produce statically linked, cross-platform executables that challenge traditional analysis techniques. These binaries embed a substantial runtime and compiler-generated metadata and are compiled with aggressive optimizations that discard type inf…
Read original ↗https://arxiv.org/abs/2605.14020arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills arXiv:2605.13940v1 Announce Type: new Abstract: Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills useful, but it also introduces a new security problem: a malicious skill does not need to ask the model to perform an obviously harmful ac…
Read original ↗https://arxiv.org/abs/2605.13940arxiv_cs_cr · tlp:amber · 5/15/2026, 4:00:00 AM
XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles arXiv:2605.13922v1 Announce Type: new Abstract: During the last few years, the term Mechanistic Interpretability, a specific area, under the umbrella of explainable artificial intelligence (XAI), has been introduced, to explain the decisions made by complex machine learning (ML) models in critical systems like UAV intrusion detection systems…
Read original ↗https://arxiv.org/abs/2605.13922arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
CLOUDBURST: Cloud-Layer Observations Using Beacons for Unified Real-time Surveillance and Threat Attribution arXiv:2605.12976v1 Announce Type: new Abstract: Modern cloud-native environments present a fundamentally different exfiltration threat surface than traditional file-based scenarios. Attackers targeting AWS, GCP, Azure, and OCI steal S3 presigned URLs, container images, Kubernetes secrets, Terraform state modules, and IAM role tokens -- artefacts that existing honeytok…
Read original ↗https://arxiv.org/abs/2605.12976arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills arXiv:2605.12875v1 Announce Type: new Abstract: Programmatic skills in LLM ecosystems consist of a natural-language description and executable implementation files. Users and LLMs rely on the description to understand the skill's scope. However, the implementation may perform security-relevant operations, such as credential access, network communication, or command execut…
Read original ↗https://arxiv.org/abs/2605.12875arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models arXiv:2605.13338v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) are increasingly integrated into systems requiring reliable multi-step inference, yet this growing dependence exposes new vulnerabilities related to computational availability. In particular, LRMs exhibit a tendency to "overthink", producing excessively long and redundant reasoning trace…
Read original ↗https://arxiv.org/abs/2605.13338arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Insecure Despite Proven Updated: Extracting the Root VCEK Seed on EPYC Milan via a Software-Only Attack arXiv:2605.12990v1 Announce Type: new Abstract: In the official whitepaper of Secure Encrypted Virtualization with Secure Nested Paging (SEV-SNP), AMD explicitly emphasizes the capability to prevent Trusted Computing Base (TCB) rollback attacks. Cryptographically, this is realized by signing attestation reports with the Versioned Chip Endorsement Key (VCEK), which is deriv…
Read original ↗https://arxiv.org/abs/2605.12990arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills arXiv:2605.13044v1 Announce Type: new Abstract: LLM-powered agents can silently delete documents, leak credentials, or transfer funds on a routine user request, not because the agent was attacked, but because the skill it invoked broke its own declared safety rules. We call these specification violations: benign inputs cause a skill to breach the natural-language guardrails in its own specifica…
Read original ↗https://arxiv.org/abs/2605.13044arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival Analysis arXiv:2605.12869v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary success/failure metrics, failing to capture the temporal dynamics of how attacks succeed under persistent adve…
Read original ↗https://arxiv.org/abs/2605.12869arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Watermarking Should Be Treated as a Monitoring Primitive arXiv:2605.13095v1 Announce Type: new Abstract: Watermarking is widely proposed for provenance, attribution, and safety monitoring in generative models, yet is typically evaluated only under adversaries who attempt to evade detection or induce false positives at the level of individual samples. We argue that watermarking should be treated as a monitoring primitive, and that internal monitoring is unavoidable given per-…
Read original ↗https://arxiv.org/abs/2605.13095arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Security Incentivization: An Empirical Study of how Micropayments Impact Code Security arXiv:2605.13100v1 Announce Type: new Abstract: Security often receives insufficient developer attention because it does not directly generate visible value, leading to underinvestment in practice. We evaluate a countermeasure by team-level incentives tied to measurable security improvements over time. Our semi-automated mechanism aggregates static analysis findings from Bearer, Detekt, an…
Read original ↗https://arxiv.org/abs/2605.13100arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models arXiv:2605.12529v1 Announce Type: new Abstract: In recent trends, one can observe Large Language Models (LLMs) are exposed to backdoor attacks where vicious triggers added during training or model editing to elicit harmful outputs on specific input patterns while maintaining clean performance on normal inputs. Legitimate watermarks used as ownership signatures sh…
Read original ↗https://arxiv.org/abs/2605.12529arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
HE-PIM: Demystifying Homomorphic Operations on a Real-world Processing-in-Memory System arXiv:2605.12841v1 Announce Type: new Abstract: Homomorphic encryption (HE) enables computation over encrypted data, offering strong privacy guarantees for untrusted computing environments. Practical adoption remains limited by high computational complexity, large ciphertext sizes, and substantial data movement. Processor-centric architectures (CPUs, GPUs, ASICs) hit fundamental bottlenec…
Read original ↗https://arxiv.org/abs/2605.12841arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense arXiv:2605.13115v1 Announce Type: new Abstract: Diffusion models depend on pseudo-random number generators (PRNGs) for latent noise sampling. We present DiffusionHijack, a supply-chain backdoor attack that hijacks the PRNG to deterministically control generated images. A malicious PRNG, injected via compromised packages, forces pixel-perfect reproduction of attacker-chose…
Read original ↗https://arxiv.org/abs/2605.13115arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It? arXiv:2605.12827v1 Announce Type: new Abstract: Graph neural networks (GNNs) deployed as cloud services can be \emph{stolen} through \emph{model-extraction attacks}, which train a surrogate from query responses to reproduce the target's behaviour, and a growing line of ownership defenses tries to prevent or trace such theft. The title of this paper asks two questions: \emph{how hard is it to s…
Read original ↗https://arxiv.org/abs/2605.12827arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
CoT-Guard: Small Models for Strong Monitoring arXiv:2605.12746v1 Announce Type: new Abstract: Monitoring the chain-of-thought (CoT) of reasoning models is a promising approach for detecting covert misbehavior (i.e., hidden objectives) in code generation tasks. While large models (GPT-5, Gemini-3-Flash) can serve as effective CoT monitors, they are expensive to deploy due to the lengthy reasoning traces and high API cost, emphasizing the need for smaller, cheaper alternatives…
Read original ↗https://arxiv.org/abs/2605.12746arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Extending Blockchain Untraceability with Plausible Deniability arXiv:2605.13132v1 Announce Type: new Abstract: Traditional blockchain untraceability schemes, such as mixers and privacy coins, obscure the sender-receiver relationship by placing transfers within an anonymity set. This paper studies a stronger goal: whether the transfer event itself can be made unobservable by blending into common decentralized-finance (DeFi) activity. We introduce Deniable Covert Asset Transfe…
Read original ↗https://arxiv.org/abs/2605.13132arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous Driving arXiv:2605.12743v1 Announce Type: new Abstract: Existing physical adversarial attacks on vision-based autonomous driving induce time-evolving perception errors, including biased object tracking or trajectory prediction, through (i) sophisticated physical patch inducing detection box drift when entering the view distance, or (ii) dynamically changing patches that cause different perc…
Read original ↗https://arxiv.org/abs/2605.12743arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Empowering IoT Security: On-Device Intrusion Detection in Resource Constrained Devices arXiv:2605.13159v1 Announce Type: new Abstract: IoT devices particularly microcontrollers are challenged by their inherent limitations in processing capabilities, memory capacity, and energy conservation. Securing communication within IoT networks is further complicated by the heterogeneity of devices and the myriad of potential security threats. Our study introduces a lightweight model th…
Read original ↗https://arxiv.org/abs/2605.13159arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Persona-Conditioned Adversarial Prompting (PCAP): Multi-Identity Red-Teaming for Enhanced Adversarial Prompt Discovery arXiv:2605.12565v1 Announce Type: new Abstract: Existing automated red-teaming pipelines often miss attacks that depend on attacker identity, framing, or multi-turn tactics. This under-coverage underestimates real-world risk. We introduce Persona-Conditioned Adversarial Prompting (PCAP), which conditions adversarial search on attacker personas and strategy c…
Read original ↗https://arxiv.org/abs/2605.12565arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
OverrideFuzz: Semantic-Aware Grammar Fuzzing for Script-Runtime Vulnerabilities arXiv:2605.12563v1 Announce Type: new Abstract: Script-language runtimes such as Python, Lua, and JavaScript are widely deployed in security sensitive contexts, yet they remain difficult to test because valid inputs must satisfy syntax, dynamic type constraints, and object-level semantics. Existing grammar and reflection-based fuzzers improve syntactic validity and interface reachability, but the…
Read original ↗https://arxiv.org/abs/2605.12563arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters arXiv:2605.13163v1 Announce Type: new Abstract: Foundation models and low-rank adapters enable efficient on-device generative AI but raise risks such as intellectual property leakage and model recovery attacks. Existing defenses are often impractical because they require retraining or access to the original dataset. We propose LoREnc, a training-free framework that secures both FMs and adapters via …
Read original ↗https://arxiv.org/abs/2605.13163arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Ghost in the Context: Measuring Policy-Carriage Failures in Decision-Time Assembly arXiv:2605.12535v1 Announce Type: new Abstract: LM agents do not act on raw interaction history; they act on a bounded decision state assembled by truncation, summarization, reordering, and rewriting. If directive-bearing state is dropped, weakened, or rebound during that step, an agent can cross a policy boundary without prompt override, model changes, or persistent-memory compromise. We stud…
Read original ↗https://arxiv.org/abs/2605.12535arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks arXiv:2605.13214v1 Announce Type: new Abstract: Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model. These guarantees, however, have been confined to stylised architectures of limited practical relevance, leaving open whether comparable undetectability extends to modern, end-to-end…
Read original ↗https://arxiv.org/abs/2605.13214arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
ThermalTap: Passive Application Fingerprinting in VR Headsets via Thermal Side Channels arXiv:2605.12927v1 Announce Type: new Abstract: Standalone virtual reality (VR) headsets process highly sensitive personal, professional, and health-related data, yet their susceptibility to non-contact physical side channels remains largely unexplored. Existing side-channel attacks typically require malicious software execution or physical access to peripherals, making them conspicuous a…
Read original ↗https://arxiv.org/abs/2605.12927arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Automatic Detection of Reference Counting Bugs in Linux Kernel Drivers arXiv:2605.13246v1 Announce Type: new Abstract: Reference counting bugs in Linux kernel drivers can lead to severe resource mismanagement and security vulnerabilities. We introduce DrvHorn, a novel automated tool to detect these bugs by reducing reference counting verification to an assertion checking problem leveraging the Linux driver interface. Through efficient modeling of the Linux kernel and aggress…
Read original ↗https://arxiv.org/abs/2605.13246arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
From Compression to Accountability: Harmless Copyright Protection for Dataset Distillation arXiv:2605.12942v1 Announce Type: new Abstract: Large-scale datasets have been a key driving force behind the rapid progress of deep learning, but their storage, computational, and energy costs have become increasingly prohibitive. Dataset distillation (DD) mitigates this problem by synthesizing compact yet informative datasets, thereby enabling efficient model training and storage. Ho…
Read original ↗https://arxiv.org/abs/2605.12942arxiv_cs_cr · tlp:amber · 5/14/2026, 4:00:00 AM
Context-Aware Web Attack Detection in Open-Source SIEM Systems via MITRE ATT&CK-Enriched Behavioral Profiling arXiv:2605.13337v1 Announce Type: new Abstract: Security Information and Event Management (SIEM) systems aggregate log data from heterogeneous sources to detect coordinated attacks. Traditional rule-based correlation engines struggle to classify multi-step web application attacks because they examine each event without reference to the behavioural history of the orig…
Read original ↗https://arxiv.org/abs/2605.13337