Latest threat reports & articles

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

Efficient and Sound Probabilistic Verification for AI Agents arXiv:2606.20510v1 Announce Type: new Abstract: Securing AI agents that operate in complex digital environments has become a critical need, and runtime monitoring approaches that formulate and enforce policies expressed in a formal language like Datalog offer a promising solution. However, existing approaches are restricted to deterministic policies. In many practical applications of AI agents, there is a need to e…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software arXiv:2606.20502v1 Announce Type: new Abstract: Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved. We present CWE-Trace, a framework for LLM vulnerability detection built from 834 manually curated Linux kernel samples spanning 74 CWEs. The framework enfo…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

A-COMPASS: Formal Foundations for Anonymity Analysis in Microdata arXiv:2606.20492v1 Announce Type: new Abstract: In the information age, one of the leading problems is how to ensure individual's privacy. Depending on the context in which privacy is considered, various data privacy models have emerged. However, the domain of formal verification of these models is still not sufficiently explored even when it comes to the most basic models. An attempt to verify privacy require…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems arXiv:2606.20470v1 Announce Type: new Abstract: Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with other agents. These capabilities make prompt-injection and jailbreak attacks more consequential, especially as attackers adopt model-guided automation to scale probing, prompt refinement,…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

Image Encryption Algorithm Based on Convolutional Neural Networks and Dynamic S-Box Generation arXiv:2606.20444v1 Announce Type: new Abstract: The paper proposes a dynamic approach to image encryption, combining the use of Convolutional Neural Networks (CNNs) and classical cryptography to improve the security and flexibility of image encryption. The main concept is to create adaptive Substitution boxes (S-boxes) based on characteristics that are learned by a trained CNN. The…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

Secure Coding Drift in LLM-Assisted Post-Quantum Cryptography Development: A Gamified Fix arXiv:2606.19474v1 Announce Type: new Abstract: The transition to Post Quantum Cryptography (PQC) introduces considerable implementation complexity, requiring strict adherence to constant-time execution, side channel resistance, and precise parametrisation. Simultaneously, large language models (LLMs) are heavily embedded in software development workflows, including cryptographic engine…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

Multi-View Decompilation for LLM-Based Malware Classification arXiv:2606.20436v1 Announce Type: new Abstract: Malware analysts often inspect compiled binaries through decompiled pseudo-C, when source code is unavailable. Recent work suggests that large language models (LLMs) can assist this process by classifying decompiled code as benign or malicious, but existing pipelines typically rely on a single decompiler view. We argue that this assumption is fragile: decompilers are…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

LLM agent safety, multi-turn red-teaming, jailbreak benchmarks, adversarial robustness, safety-critical systems arXiv:2606.20408v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized. We present NRT-Bench, a benchmark for multi-turn red-teaming of LLM agents acting as operators of a safety…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

Quantization as a Malicious Task: Removing Quantization-Conditioned Backdoors via Task Arithmetic arXiv:2606.20254v1 Announce Type: new Abstract: Model quantization is widely adopted to reduce memory usage and inference cost when deploying deep neural networks on resource-constrained devices. However, recent studies have revealed a new security threat known as Quantization-Conditioned Backdoors (QCBs), where a model behaves normally in full precision but activates malicious …

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

TrustMix: How to Mix Messages in a Mobile Ad-hoc Network arXiv:2606.20251v1 Announce Type: new Abstract: Mix networks are a highly effective way to achieve anonymity, defending against a wide range of traffic-analysis attacks. However, mix networks are usually designed for infrastructure networks and cannot be directly applied in the context of mobile ad hoc networks (MANETs). The few existing solutions for MANETs require advance knowledge of the topology or a trusted centra…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

FloatDoor: Platform-Triggered Backdoors in LLMs arXiv:2606.19535v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in sensitive settings such as software engineering, where their outputs directly shape downstream artifacts. Recent work has shown that an identical model can produce measurably different outputs depending on the deployment platform, a consequence of non-associative floating-point arithmetic and divergent kernel implementation…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

G-Lox: Group-Adaptive, Privacy-Preserving Bridge Distribution with Two-Party Computation arXiv:2606.19620v1 Announce Type: new Abstract: We present G-Lox (group-adaptive Lox), a bridge-distribution system that preserves Lox-style distributor blindness while enabling hidden, stateful group-level adaptation. G-Lox places adaptive assignment logic behind a two-server privacy wall, so no single server learns group identifiers or group-to-bridge assignments. Private state access …

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

PUFFERDOS: Efficient and Effective Attack String Generation for Regular Expression Denial of Service Vulnerabilities arXiv:2606.19654v1 Announce Type: new Abstract: ReDoS attacks constitute a critical class of resource-exhaustion vulnerabilities. In such attacks, adversaries exploit the pathological worst-case execution behavior of regular expression (regex) engines to induce highly asymmetric computational workloads, ultimately exhausting system resources and degrading serv…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots arXiv:2606.19660v1 Announce Type: new Abstract: Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applications, yet existing defenses operate at isolated pipeline stages and remain incomplete. Input filters cannot inspect retrieved documents, while output monitors cannot prevent malicious payloads from reaching the mode…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

GNSS Spoofing Threat for V2X communications arXiv:2606.20215v1 Announce Type: new Abstract: Global Navigation Satellite Systems (GNSS) constitute a core technology for delivering crucial positioning, navigation, and timing (PNT) services in the Vehicle-to-Everything (V2X) domain, where they are indispensable for generating Cooperative Awareness Messages (CAM) that uphold network reliability and vehicular safety. Yet, GNSS signals are acutely exposed to spoofing, an advanced …

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

When Global Gating Is Enough: Admission-Time Hubness Control in Anisotropic Vector Retrieval Systems arXiv:2606.19692v1 Announce Type: new Abstract: Vector hubness, where a few points become nearest neighbors of many queries, creates a poisoning risk in retrieval-augmented generation (RAG): one injected document can influence unrelated requests. Existing defenses use periodic reverse-kNN scans, leaving an exposure window and repeated corpus-wide work. We study admission-time…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling arXiv:2606.19755v1 Announce Type: new Abstract: Speculative inference accelerates large language model (LLM) decoding but provides no inherent safety guarantees. Existing safety defenses are largely incompatible with speculative inference: they either introduce additional computation or disrupt the draft-verify mechanism, negating acceleration benefits. This reveals a fundamental incompatibility between current safe…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

DISARM: Target Electronic Device Informed Mitigation of Software Runtime Side-Channel Vulnerabilities arXiv:2606.19807v1 Announce Type: new Abstract: Program runtime or timing attacks exploit variations in a program's execution times to extract sensitive information from the program (e.g. encryption keys, sensitive variable data, intellectual property). State-of-the-art solutions to runtime side-channel attacks attempt to balance the execution time of the sensitive code for …

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

Heterogeneous LLM Debate Under Adversarial Peers: Honest Gains, Replacement Costs, and Resilience arXiv:2606.19826v1 Announce Type: new Abstract: Heterogeneous LLM debate is motivated by the promise that diverse peers correct one another, but the same exchange that carries correction also carries adversarial influence. We measure which dominates by tracking how a heterogeneous peer changes the honest agents' revision behavior: how often they change their answer, and whether …

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

Low-Cost Multi-Precision Systolic Arrays for Accelerating FHE NTTs on AI ASICs arXiv:2606.19866v1 Announce Type: new Abstract: Fully Homomorphic Encryption (FHE) ensures robust data privacy but suffers from prohibitive computational overhead. Accelerating FHE on AI hardware like Tensor Processing Units (TPUs) is promising, yet fundamentally limited by a precision mismatch: TPUs are optimized for 8-bit arithmetic, whereas FHE and its critical parts such as the Number Theoreti…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

Accelerating Trust Convergence in IIoT: A ML Approach for Dynamic Network Conditions arXiv:2606.20214v1 Announce Type: new Abstract: In Industrial Internet of Things (IIoT) environments, trust management plays a vital role in securing systems, especially when dealing with resource-constrained devices. Traditional trust models often overlook the impact of fluctuating network quality, leading to slower trust convergence and inaccurate assessments. In this paper, we propose a d…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

FFinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming arXiv:2606.19887v1 Announce Type: new Abstract: Existing safety benchmarks target general adversarial scenarios but miss finance-specific risks. Financial LLMs face regulatory compliance violations, fraud facilitation, and systemic trust erosion that require targeted evaluation. We introduce FinRED, an expert-guided red-teaming framework for financial LLM safety evaluation d…

arxiv_cs_cr · tlp:amber · 6/19/2026, 4:00:00 AM

AutoTam: Specifying Secure Protocol Implementations with Tamarin Model Generation arXiv:2606.19937v1 Announce Type: new Abstract: Formal verification is a challenging but important task for ensuring the security of cryptographic protocols. While modern protocol verification tools significantly reduce verification effort, modelling remains challenging to practitioners without a background in formal verification. In addition, transferring verification results to a concrete pro…

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

Confident yet Concerned: Inconsistencies in Computing Students' Attitudes on Cybersecurity arXiv:2606.18541v1 Announce Type: new Abstract: Today's young adults are most immersed in technology, leading in feelings of powerlessness in managing online privacy across many platforms, and particularly susceptible to phishing attacks. This raises questions about their general, wide-ranging attitudes towards and management of cybersecurity. How do young, tech-savvy adults approach c…

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

TopVenues: A Reproducible Corpus and Tooling Substrate for Cybersecurity Literature Reviews arXiv:2606.18320v1 Announce Type: new Abstract: Cybersecurity literature reviews require a reproducible denominator: the set of papers that a protocol includes before screening and synthesis begin. Today, that denominator is often reconstructed from publisher portals, bibliographic indices, and scholarly application programming interfaces (APIs) whose coverage, formats, and query sema…

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents arXiv:2606.18356v1 Announce Type: new Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects. Existing evaluations often collapse these stages into a single attack success rate, making it difficult to tell…

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

Evaluating the Effectiveness of LLMs in Aiding Compliance Testing of PKCS#1-v1.5 arXiv:2606.18405v1 Announce Type: new Abstract: Testing implementations of binary protocols for specification compliance requires inputs that satisfy both structural and semantic constraints. Purely random generation and primitive mutations are often insufficient for exploring semantically meaningful behaviors in protocols that rely on Type-Length-Value (TLV) encoding, yet domain-specific compli…

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

Understanding the "Airport" Censorship Circumvention Ecosystem in China arXiv:2606.18427v1 Announce Type: new Abstract: In China, a burgeoning underground market sells citizens subscription-based censorship circumvention proxies known as ''airports''. We present the first systematic study of this ecosystem, combining user surveys, social media analysis, and active network measurements. We find that airports are by far the most popular off-the-shelf censorship circumvention t…

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

Ghost Vectors: Soft-Deleted Embeddings Remain Reconstructible in HNSW Vector Databases arXiv:2606.18497v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) allows large language models to access external and private corpora for factual, domain-specific responses. Modern RAG pipelines use hierarchical navigable small world (HNSW) vector databases for efficient similarity search. When a user requests data deletion, the systems typically only mark the record as …

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

From Bits to Mixed-Radix Keys: Horner Decomposition, Uniform Sampling, and the Information-Theoretic QKD Interface of the MR-OTP arXiv:2606.18526v1 Announce Type: new Abstract: The Mixed-Radix One-Time Pad (MR-OTP) extends the classical OTP to heterogeneous alphabets while preserving perfect secrecy. We provide a practical, bias-free method to convert raw binary entropy from a QKD source into uniform mixed-radix keys by identifying Horner's method and its inverse as the natu…

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

Evaluating Prompting-Based Defenses Against Domain-Camouflaged Injection Attacks arXiv:2606.18530v1 Announce Type: new Abstract: Domain-camouflaged injection attacks embed malicious instructions in retrieved content using domain-appropriate vocabulary, evading standard detectors that rely on syntactic injection markers. When detection fails, practitioners need to know which defense architectures reduce attack success. We evaluate five prompting-based defenses (spotlighting, …

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework arXiv:2606.18532v1 Announce Type: new Abstract: AI systems are increasingly evaluated in bounded environments that combine isolation, simulation, instrumentation, supervision, and evidence capture. For physical AI, AIoT, and cyber-physical systems, this shift is not a matter of terminology: the system under test may sense, decide, actuate, communicate, and fail through physical processes, networked devices, an…

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

The Gate Is Only as Honest as Its Contracts: ContractGuard for the Contract Layer of Risk-Aware Causal Gating arXiv:2606.18550v1 Announce Type: new Abstract: Risk-Aware Causal Gating (RACG) defends tool-augmented LLM agents against indirect prompt injection by removing dangerous tools from the agent's visible action space, so that even a fully injection-compliant agent cannot call a tool it cannot see. We make three points. First, this structural guarantee does not eliminate…

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

MIDS: Detecting Stealthy Masquerade and Tampering Attacks on CAN Bus via Bidirectional Mamba arXiv:2606.18599v1 Announce Type: new Abstract: The Controller Area Network (CAN) protocol is the primary communication standard for Electronic Control Units (ECUs) in modern vehicles, but its lack of encryption and authentication exposes it to a range of security threats. Existing intrusion detection systems are largely tuned to fabrication-style attacks (DoS, fuzzing, ID spoofing r…

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

Code-Augur: Agentic Vulnerability Detection via Specification Inference arXiv:2606.18619v1 Announce Type: new Abstract: The advent of agentic vulnerability detection is already becoming a watershed moment for software security. Audits conducted entirely by autonomous LLM agents are uncovering critical vulnerabilities in fundamental software underpinning digital society. Many of these vulnerabilities remained masked for years, surfacing only now with AI agents. Yet the reason…

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

TGCM: Topic-Guided Generative Disentanglement of Interleaved APT Technique Sequences arXiv:2606.18651v1 Announce Type: new Abstract: In enterprise environments, multiple Advanced Persistent Threat (APT) campaigns often unfold concurrently, producing audit logs in which attack techniques across actors (sources) are interleaved over time. This setting naturally gives rise to an Unknown-K Interleaved Sequence Demixing (UKISD) problem: recovering multiple latent campaigns from a…

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications arXiv:2606.18673v1 Announce Type: new Abstract: Large language model (LLM)-based applications rely on system prompts to encode core logic and developer-defined constraints, making these prompts important intellectual property. However, system prompts are vulnerable to prompt leaking attacks. Although prior work has shown such attacks in controlled settings, their prevalence, causes, and …

arxiv_cs_cr · tlp:amber · 6/18/2026, 4:00:00 AM

Image Prompt Reconstruction Attacks on Distributed MLLM Inference Frameworks arXiv:2606.18710v1 Announce Type: new Abstract: Distributed large language model (LLM) inference frameworks connect isolated consumer-grade devices for large-scale model inference, substantially reducing hardware constraints. However, recent studies show that intermediate embeddings transmitted among participants can leak private prompts. As LLMs evolve into multimodal LLMs (MLLMs), this risk extend…