8598 matches found
WordPress Authorizer 3.15.3 Privilege Escalation Scanner
WordPress Authorizer versions through 3.15.3 contain an unauthenticated privilege escalation vulnerability. The supplied Python tool passively detects installed versions and optionally inspects Azure OAuth2 configuration...
Chaining Skills to Hijack LLM Agents
LLM agents use skills to improve performance on specialized tasks. To complete a user request, an agent may invoke several skills in sequence, allowing information produced under one skill to guide the next. Because skills may come from open-source repositories, this handoff can also carry...
Homomorphic Advantage Operator: Stabilizing Reinforcement Learning under Fully Homomorphic Encryption Constraints
Privacy-preserving machine learning presents significant deployment challenges on the cloud for intelligent systems with confidential data. Fully Homomorphic Encryption FHE offers a compelling solution for secure computation, preserving data confidentiality of cloud computations. However, applyin...
TREX MES 6.07.17.00090 / TrexDCAS MES 6.05.14.00074 SQL Injection
TREX MES versions 6.07.17.00090 and earlier and TrexDCAS MES versions 6.05.14.00074 and earlier contain an SQL injection vulnerability in web API sql parameter handling...
CITADEL: CWE-Guided Insertion of Hardware Trojans Via Analysis of DFG-Enabled LLMs
The increasing sophistication of Hardware Trojans HTs and system-level vulnerabilities poses significant risks to modern integrated circuits. However, constructing realistic HT scenarios, remains a substantial burden: researchers must manually analyze complex RTL structures, identify plausible...
Sleeping Secrets: How Fine-Tuning Reawakens Privacy Risks in Language Models
Beyond adapting Large Language Models LLMs to specialized applications, fine-tuning has recently been shown to recover private information that is no longer accessible through direct queries. Previous fine-tuning recovery attacks, however, require genuine private supervision drawn from the same...
From Network Intrusion Detection to Blockchain-Backed Endpoint Detection and Response: Mapping the Landscape of Decentralized Detection-And-Response Architectures
While the literature on blockchain-assisted intrusion detection and prevention systems IDS/IPS for Internet of Things IoT and Industrial Internet of Things IIoT networks is mature, existing systematic reviews suffer from two critical limitations: they overlook the structural shift toward modern...
game-music-emu 0.6.5 NULL Pointer Dereference / Denial of Service
A NULL pointer dereference in the AY file loader of game-music-emu libgme, the open-source video game music emulation library, allows an attacker who supplies a crafted .ay file to terminate any application that begins playback of it. Versions through 0.6.5 are affected...
A Deterministic and Auditable AI Security Risk Assessment Framework with ATLAS Aligned Executable Rules and Formal Verification
Artificial intelligence systems are increasingly deployed in high impact and safety critical settings, yet security assessment remains difficult to reproduce and defend under audit. Existing approaches often rely on narrative checklists or assessor driven scoring, and they lack an explicit, machi...
Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM
GraphRAG pipelines construct auxiliary structures during offline indexing--semantic summaries, hierarchical edges, and pre-computed scores--that determine how retrieval is prioritised at query time. Prior attacks target only instance-level components nodes, edges, triples, overlooking these...
MIRROR: Multipath Quorum Integrity for LLM Multi-Agent Communication
Inter-agent communication is central to Large Language Model Multi-Agent Systems LLM-MAS, but it introduces an underexplored vulnerability: Agent-in-the-Middle AiTM attacks that manipulate messages in transit without compromising the agents themselves. Prior work reports Attack Success Rates ASR...
A Structured State Space Sequence Model for Multi-Class Classification of Malware
By 2030, Internet of Things IoT devices are projected to reach 40 billion, with fast-paced technological advancements in fields such as industry, healthcare, agriculture, automobiles, and building/home automation systems. This expansion has created a large attack surface for cybercrime, as the...
High-Quality Data Do Not Mean Safe! Poisoning LLMs after Data Selection
Safety-aligned Large Language Models remain vulnerable to fine-tuning on small sets of harmful or benign-looking samples. However, prior studies typically assume that poisoned samples directly enter downstream fine-tuning, overlooking quality-based selection in practical training pipelines. To fi...
Protocol Integration of Physical Layer Deception into EAP-TEAP Wi-Fi Authentication
Credential-based Extensible Authentication Protocol EAP authentication cannot distinguish a legitimate credential holder from an adversary using compromised credentials. Physical Layer Deception PLD complements credential-based authentication by exposing a deceptive primary object over a primary...
Xalgorix Autonomous AI Pentesting Agent 4.6.128
Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...
Learnt Attacks on Quantum Key Distribution under Channel Noise and Device Drift
Quantum key distribution QKD links are provisioned from security analyses of stationary channels, whereas the devices that determine the channel drift between recalibrations. Whether an eavesdropper who cannot alter the channel's own noise gains by following that drift has not been quantified...
Out of Sync, out of Sight: Phantom State Attacks against IIoT Intrusion Detection
Machine learning-based intrusion detection systems IDS are critical for securing Industrial Internet of Things IIoT environments. Most adversarial research against them perturbs the feature vector or the traffic that produces it, and depends on gradient access, repeated model queries, or a learne...
Prompted to Discriminate: Generalizing Malicious-Input Probes in the Wild
LLM agents increasingly rely on activation probes as runtime monitors for prompt injection, jailbreaks, and unsafe requests, reading the model's own hidden state to catch a harmful input before the agent acts on it. A cheap, increasingly common move, borrowed from LLM-as-judge prompting, is to...
QUFIG: GNN-Based Prediction of Quantum Fault Injection Vulnerabilities with Gate-Level Precision
The growing scale and accessibility of quantum hardware exposed new reliability and security challenges in the quantum computing workflow, such as the run-time fault injection attacks in cloud-based quantum computing platforms. However, existing works fail to identify vulnerabilities with...
Joern 4.0.644
Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...
Jev-IDS: System One Models for Network Intrusion Detection
Machine-learning Network Intrusion Detection Systems IDS depend on substantial labeled datasets and task-specific training, whereas Large Language Models LLMs detection can analyze flow records directly but incurs higher inference cost and latency, with less constrained outputs. This paper presen...
game-music-emu 0.6.5 VGM Command Interpreter Missing Operand Out-Of-Bounds Read
An out-of-bounds read in the VGM command interpreter of game-music-emu libgme, the open-source video game music emulation library, allows an attacker who supplies a crafted .vgm or .vgz file to read heap memory past the end of the buffer holding the file. The read happens as soon as playback...
The Innocent Courier: Covert Exfiltration through Legitimate LLM Web Fetching
With the increasing capabilities of Large-Language-Models LLMs and LLM-based agents, users are increasingly using them to solve everyday problems, such as answering e-mails or providing programming support. Existing work has extensively investigated security and privacy risks, such as prompt...
OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents
LLM agents with tool-calling capabilities can access external services and private user data, but they may retrieve more information than a user's request explicitly requires. We study this behavior in structured tool-calling agents and term it proactive over-authorization. This setting differs...
Mitigating Private Data Leakage in LLMs with Whiteout
Modern large language models LLMs are trained on massive, largely unfiltered datasets, including content scraped from nearly every accessible website and user inputs. As a result, LLMs often memorize and reproduce personally sensitive information PSI such as birth dates, phone numbers, and home...
SuiteCRM 8.10.1 Authenticated Server-Side Request Forgery
SuiteCRM versions through 7.15.1 and 8.10.1 contain an authenticated server-side request forgery vulnerability in CalendarAccount testConnection. The proof of concept submits a supplied CalDAV server URL to demonstrate server-side request handling...
game-music-emu 0.6.5 GYM Playback Out-Of-Bounds Read
An out-of-bounds read in the GYM playback path of game-music-emu libgme, the open-source video game music emulation library, allows an attacker who supplies a crafted .gym file to read heap memory past the end of the allocation holding the file contents, potentially terminating the process...
game-music-emu 0.6.5 VGM Command Interpreter Out-Of-Bounds Read / DoS
An out-of-bounds read in the VGM command interpreter of game-music-emu libgme, the open-source video game music emulation library, allows an attacker who supplies a crafted .vgm or .vgz file to crash the hosting process or to have adjacent heap memory influence the rendered audio, via a PCM seek...
KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus on knowledge-based assessments or end-to-end agentic tasks, and do not directly measure LLMs' ability to generate executable...
System-Level Optimization beyond Cryptographic Kernels: An ML-KEM Case Study on Arm Cortex-M7
Recent work on embedded post-quantum cryptography has focused primarily on instruction-level optimization, including arithmetic-kernel improvements, assembly tuning, register allocation, and instruction scheduling. Using the Module-Lattice-Based Key-Encapsulation Mechanism ML-KEM on an Arm...
"I'm Trying Not to Get Hacked:" How Adults with Intellectual and Developmental Disabilities Navigate Security and Privacy Notifications
Security and privacy notifications, such as login alerts, spam email warnings, and cookie consent requests, play a critical role in shaping users' responses to digital risks. Yet most notifications overlook cognitive accessibility, limiting their effectiveness for people with intellectual and...
Evaluating and Improving the Robustness of Large Language Models to Input Sequence Variations
Large language models LLMs in production systems face prompt injections, trojans backdoors, and manipulation of automatic quality metrics. This thesis develops models, methods, and algorithms for evaluating and improving LLM robustness to adversarial input sequence variations. We propose Rstabf, ...
Autonomous OSS Threat Detection Via Taxonomy-Aligned LLMs
Open source software OSS ecosystems face growing threats from sophisticated supply chain attacks including typosquatting, dependency confusion, Trojan Source obfuscation, malicious build injection, and CI/CD pipeline poisoning. Existing detection approaches rely on signature-based tools and...
SideKernel: A Usable MicroVM Sandbox for AI Coding Agents on MacOS
AI coding agents are untrusted system components, yet they require autonomy on the developer machines they run on. This contradiction is a security problem. Sandboxes provide an isolated environment, but for local macOS development, the existing local, open-source options for AI coding agents are...
TREX MES 6.07.17.00090 Missing Authentication
TREX MES version 6.07.17.00090 and earlier, and TrexDCAS MES version 6.05.14.00074 and earlier, contain a missing server-side authentication issue in the /api/GetDataJSON3 endpoint that permits unauthenticated data queries...
A Hybrid Approach to Malware Detection: Integrating Few-Shot Model-Agnostic Meta-Learning with Autoencoders
Ransomware has emerged as a major cybersecurity threat, with incidents increasing in frequency and impact across critical sectors. These attacks are typically launched through phishing emails, malicious downloads, or exploitation of software vulnerabilities to gain system access. Once inside, the...
A Resource-Aware Behavior Reconstruction and Hierarchical Semantic Learning Framework for Host Intrusion Detection
System calls syscalls record key interactions between running programs and the operating system kernel, providing fine-grained and minimally intrusive data for host-based intrusion detection systems HIDS deployed in cloud and other modern computing environments. However, existing methods often...
The Achilles' Heel of Partial Reconfiguration: Optical Side-Channel Leakage on the 7-Series ICAP
Major FPGA manufacturers have incorporated bitstream encryption to protect sensitive configuration data. However, for the most widely used FPGA families, multiple attacks against unpatchable protection schemes hard-wired into the devices can bypass or fully break them, making patchable schemes...
GNSS Spoofing in Mobile Devices: A Survey on Impact and Countermeasures
Smartphones rely on Global Navigation Satellite System GNSS-based positioning for many of the functions they execute everyday. The GNSS receivers embedded in smartphones are susceptible to anthropogenic radio frequency interference attacks in the forms of jamming and spoofing due to the low-power...
SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified Examples
As machine learning increasingly relies on public, untrusted data sources, data poisoning attacks, which inject malicious examples into training data to induce misclassification of a chosen target, pose a growing threat. Existing defenses either assume zero ground-truth information about which...
Intent-Hiding Jailbreaks: An Information-Theoretic Framework for Compositional Attacks
Recent work has shown that large language models LLMs can be vulnerable to jailbreak attacks in which harmful intent is obscured through composition with benign tasks. A harmful request refused in isolation may elicit a different response when embedded within a larger, seemingly benign query. We...
MediaWiki CommonsMetadata 1.46 License URL Cross Site Scripting
MediaWiki CommonsMetadata extension versions 1.43, 1.45, and 1.46 contain a cross site scripting vulnerability through insufficient validation of license URLs. The supplied proof of concept checks local API metadata for an executable javascript: URL...
Security Properties of Neural Networks As Decision Problems
Certifying a deployed neural network raises decision problems that the verification literature has not classified: whether the model carries a backdoor planted in its training data, whether a fault in its stored parameters can drive it into an unsafe state, whether its output leaks a private part...
OpenSSL Toolkit 3.5.9
OpenSSL is a robust, fully featured Open Source toolkit implementing the Secure Sockets Layer and Transport Layer Security protocols with full-strength cryptography world-wide. This is the 3.6 release...
Karma Pro 0.12
Karma Pro is an open source code review tool written in Swift that can assist code reviewers with a multitude of useful tools. Karma Pro is a macOS source-code security scanner AST base and Heuristics that statically analyses projects in multiple languages. It's backed by an ML classifier trained...
Memetic Trojans: Social Contagions As Carriers of Adversarial Payloads in Agent Networks
Autonomous large language model LLM agents increasingly interact in network environments where adversarial content can propagate between agents. Known attacks include agent worms, which spread through self-replicating prompt injections or configuration compromises. We introduce memetic trojans, a...
Quantum Secret Sharing and Error Correction Vs No-Cloning
Secret sharing is ubiquitous throughout cryptography. All possible access structures are classically feasible, and in the case of threshold access structures, the protocols are even very efficient. However, when moving to the quantum setting, the no-cloning theorem shows that many access structur...
PrivCert: Certifying Statement Support under Differential Privacy
Differentially private DP text generation can protect individual records, but privacy alone does not specify what evidence a released statement carries about the underlying data. We identify this as an evidence gap: a private report may contain plausible claims without indicating whether they are...
Backdoor Purification for LoRA-Tuned LLMs Via Null-Space Projection
With the rapid adoption of large language models LLMs and parameter-efficient fine-tuning PEFT methods, the risk of backdoor attacks has become more severe. Existing backdoor purification methods typically rely on at least one of the strong assumptions, such as prior knowledge of triggers, access...