7364 matches found
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
Multi-turn interactions with language models LMs pose critical safety risks, as harmful intent can be strategically spread across exchanges. Yet, the vast majority of prior work has focused on single-turn safety, while adaptability and diversity remain among the key challenges of multi-turn...
WalletProbe: a Testing Framework for Browser-Based Cryptocurrency Wallet Extensions
Serving as the first touch point for users to the cryptocurrency world, cryptocurrency wallets allow users to manage, receive, and transmit digital assets on blockchain networks and interact with emerging decentralized finance DeFi applications. Unfortunately, cryptocurrency wallets have always...
Leveraging Vertical Public-Private Split for Improved Synthetic Data Generation
Differentially Private Synthetic Data Generation DP-SDG is a key enabler of private and secure tabular-data sharing, producing artificial data that carries through the underlying statistical properties of the input data. This typically involves adding carefully calibrated statistical noise to...
MULTI-LF: a Unified Continuous Learning Framework for Real-Time DDoS Detection in Multi-Environment Networks
Detecting Distributed Denial of Service DDoS attacks in Multi-Environment M-En networks presents significant challenges due to diverse malicious traffic patterns and the evolving nature of cyber threats. Existing AI-based detection systems struggle to adapt to new attack strategies and lack...
Improved MST3 Encryption Scheme Based on Small Ree Groups
This article presents an encryption scheme based on the small Ree groups. We propose utilizing the small Ree group structure to enhance the overall security parameters of the encryption scheme. By extending the logarithmic signature to encompass the entire group and modifying the encryption...
RAID: an In-Training Defense against Attribute Inference Attacks in Recommender Systems
In various networks and mobile applications, users are highly susceptible to attribute inference attacks, with particularly prevalent occurrences in recommender systems. Attackers exploit partially exposed user profiles in recommendation models, such as user embeddings, to infer private attribute...
Clustering and Analysis of User Behaviour in Blockchain: a Case Study of Planet IX
Decentralised applications dApps that run on public blockchains have the benefit of trustworthiness and transparency as every activity that happens on the blockchain can be publicly traced through the transaction data. However, this introduces a potential privacy problem as this data can be track...
How to Enhance Downstream Adversarial Robustness (Almost) without Touching the Pre-Trained Foundation Model?
With the rise of powerful foundation models, a pre-training-fine-tuning paradigm becomes increasingly popular these days: A foundation model is pre-trained using a huge amount of data from various sources, and then the downstream users only need to fine-tune and adapt it to specific downstream...
From Cyber Threat to Data Shield: Constructing Provably Secure File Erasure with Repurposed Ransomware Cryptography
Ransomware has emerged as a persistent cybersecurity threat,leveraging robust encryption schemes that often remain unbroken even after public disclosure of source code. Motivated by the technical resilience of such mechanisms, this paper presents SEER Secure and Efficient Encryption-based Erasure...
Exploring Backdoor Attack and Defense for LLM-Empowered Recommendations
The fusion of Large Language Models LLMs with recommender systems RecSys has dramatically advanced personalized recommendations and drawn extensive attention. Despite the impressive progress, the safety of LLM-based RecSys against backdoor attacks remains largely under-explored. In this paper, we...
On-Device Watermarking: a Socio-Technical Imperative for Authenticity in the Age of Generative AI
As generative AI models produce increasingly realistic output, both academia and industry are focusing on the ability to detect whether an output was generated by an AI model or not. Many of the research efforts and policy discourse are centered around robust watermarking of AI outputs. While...
Measuring Computational Universality of Fully Homomorphic Encryption
Many real-world applications, such as machine learning and graph analytics, involve combinations of linear and non-linear operations. As these applications increasingly handle sensitive data, there is a significant demand for privacy-preserving computation techniques capable of efficiently...
Cartesian Merkle Tree
This paper introduces the Cartesian Merkle Tree, a deterministic data structure that combines the properties of a Binary Search Tree, a Heap, and a Merkle tree. The Cartesian Merkle Tree supports insertions, updates, and removals of elements in $O\log n$ time, requires $n$ space, and enables...
Blockchain Application in Metaverse: a Review
In recent years, the term Metaverse emerged as one of the most compelling concepts, captivating the interest of international companies such as Tencent, ByteDance, Microsoft, and Facebook. These company recognized the Metaverse as a pivotal element for future success and have since made significa...
FLSSM: a Federated Learning Storage Security Model with Homomorphic Encryption
Federated learning based on homomorphic encryption has received widespread attention due to its high security and enhanced protection of user data privacy. However, the characteristics of encrypted computation lead to three challenging problems: "computation-efficiency", "attack-tracing" and...
WordPress SoftClever Limited Sync Posts 1.0 Shell Upload
WordPress SoftClever Limited Sync Posts plugin version 1.0 suffers from a remote shell upload vulnerability...
Token-Level Constraint Boundary Search for Jailbreaking Text-To-Image Models
Recent advancements in Text-to-Image T2I generation have significantly enhanced the realism and creativity of generated images. However, such powerful generative capabilities pose risks related to the production of inappropriate or harmful content. Existing defense mechanisms, including prompt...
The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections
A Large Language Model LLM powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces GUIs of relevant apps, often visually, inferring necessary sequenc...
Cybersecurity through Entropy Injection: a Paradigm Shift from Reactive Defense to Proactive Uncertainty
Cybersecurity often hinges on unpredictability, with a system's defenses being strongest when sensitive values and behaviors cannot be anticipated by attackers. This paper explores the concept of entropy injection-deliberately infusing randomness into security mechanisms to increase...
R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
Vision-language models VLMs, such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstream tasks. However, due to their inherent vulnerability and the common practice of selecting from a limited set of...
KubeFence: Security Hardening of the Kubernetes Attack Surface
Kubernetes K8s is widely used to orchestrate containerized applications, including critical services in domains such as finance, healthcare, and government. However, its extensive and feature-rich API interface exposes a broad attack surface, making K8s vulnerable to exploits of software...
A Unified Hardware Accelerator for Fast Fourier Transform and Number Theoretic Transform
The Number Theoretic Transform NTT is an indispensable tool for computing efficient polynomial multiplications in post-quantum lattice-based cryptography. It has strong resemblance with the Fast Fourier Transform FFT, which is the most widely used algorithm in digital signal processing. In this...
Improving Statistical Privacy by Subsampling
Differential privacy DP considers a scenario, where an adversary has almost complete information about the entries of a database This worst-case assumption is likely to overestimate the privacy thread for an individual in real life. Statistical privacy SP denotes a setting where only the...
Making Acoustic Side-Channel Attacks on Noisy Keyboards Viable with LLM-Assisted Spectrograms' "Typo" Correction
The large integration of microphones into devices increases the opportunities for Acoustic Side-Channel Attacks ASCAs, as these can be used to capture keystrokes' audio signals that might reveal sensitive information. However, the current State-Of-The-Art SOTA models for ASCAs, including...
Progent: Programmable Privilege Control for LLM Agents
LLM agents are an emerging form of AI systems where large language models LLMs serve as the central component, utilizing a diverse set of tools to complete user-assigned tasks. Despite their great potential, LLM agents pose significant security risks. When interacting with the external world, the...
Superintelligence Strategy: Expert Version
Rapid advances in AI are beginning to reshape national security. Destabilizing AI developments could rupture the balance of power and raise the odds of great-power conflict, while widespread proliferation of capable AI hackers and virologists would lower barriers for rogue actors to cause...
Research on CNN-BiLSTM Network Traffic Anomaly Detection Model Based on MindSpore
With the widespread adoption of the Internet of Things IoT and Industrial IoT IIoT technologies, network architectures have become increasingly complex, and the volume of traffic has grown substantially. This evolution poses significant challenges to traditional security mechanisms, particularly ...
Designing AI-Enabled Countermeasures to Cognitive Warfare
Foreign information operations on social media platforms pose significant risks to democratic societies. With the rise of Artificial Intelligence AI, this threat is likely to intensify, potentially overwhelming human defenders. To achieve the necessary scale and tempo to defend against these...
FlexiContracts: a Novel and Efficient Scheme for Upgrading Smart Contracts in Ethereum Blockchain
Blockchain technology has revolutionized contractual processes, enhancing efficiency and trust through smart contracts. Ethereum, as a pioneer in this domain, offers a platform for decentralized applications but is challenged by the immutability of smart contracts, which makes upgrades cumbersome...
Concept Enhancement Engineering: a Lightweight and Efficient Robust Defense against Jailbreak Attacks in Embodied AI
Embodied Intelligence EI systems integrated with large language models LLMs face significant security risks, particularly from jailbreak attacks that manipulate models into generating harmful outputs or executing unsafe physical actions. Traditional defense strategies, such as input filtering and...
The Voynich Codex Decoded: Statistical Symbolism and Scroll-Wide Logic
This paper introduces a structured decoding framework for the Voynich Manuscript, based on mathematical rhythm, symbolic transformation, and glyph-level recursion. Rather than interpret symbols phonetically, this method decodes them by structural roles and spatial pacing. Using scroll-wide...
Can LLMs Handle WebShell Detection? Overcoming Detection Challenges with Behavioral Function-Aware Framework
WebShell attacks, in which malicious scripts are injected into web servers, are a major cybersecurity threat. Traditional machine learning and deep learning methods are hampered by issues such as the need for extensive training data, catastrophic forgetting, and poor generalization. Recently, Lar...
WordPress SureTriggers All-in-One Automation Platform 1.0.78 Authentication Bypass
WordPress SureTriggers All-in-One Automation Platform plugin versions 1.0.78 and below suffer from an authentication bypass vulnerability that allows for privilege escalation...
Encryption Scheme Based on Automorphism Group of Hermitian Function Field with Homomorphic Encryption
This article proposes a comprehensive approach to implementing encryption schemes based on the automorphism group of the Hermitian function field. We utilize a three-parameter group with logarithmic representations outside the group's center. In this work, we enhance the Hermitian function...
Overcoming Bottlenecks in Homomorphic Encryption for the 2024 Mexican Federal Election
On June 2, 2024, Mexico held its federal elections. The majority of Mexican citizens voted in person at the polls in this historic election. For the first time though, Mexican citizens living outside their country were able to vote online via a web app, either on a personal device or using an...
Investigating Cybersecurity Incidents Using Large Language Models in Latest-Generation Wireless Networks
The purpose of research: Detection of cybersecurity incidents and analysis of decision support and assessment of the effectiveness of measures to counter information security threats based on modern generative models. The methods of research: Emulation of signal propagation data in MIMO systems,...
OX App Suite Cross Site Scripting / Third Party Vulnerabilities
OX App Suite has addressed multiple cross site scripting vulnerabilities as well as third party vulnerabilities. Last affected versions include 7.10.6 with various revisions...
WordPress Processing Projects 1.0.2 Shell Upload
WordPress Processing Projects plugin versions 1.0.2 and below suffer from a remote shell upload vulnerability...
Ivanti Connect Secure / Policy Secure / ZTA Gateways Remote Code Execution
Proof of concept exploit that demonstrates a stack-based buffer overflow in Ivanti Connect Secure before version 22.7R2.6, Ivanti Policy Secure before version 22.7R1.4, and Ivanti ZTA Gateways before version 22.8R2.2...
OpenSSH 10.0
OpenSSH is the premier connectivity tool for remote login with the SSH protocol. It encrypts all traffic to eliminate eavesdropping, connection hijacking, and other attacks. In addition, OpenSSH provides a large suite of secure tunneling capabilities, several authentication methods, and...
The Riskiest Connected Devices of 2025
Since 2020, Forescout Research - Vedere Labs has been monitoring the riskiest devices in organizational networks, leveraging data sourced directly from the devices themselves. This marks their fifth report in six years...
WordPress Simple Dashboard 2.0 Privilege Escalation
WordPress Simple Dashboard plugin versions 2.0 and below suffer from an unauthenticated privilege escalation vulnerability...
OpenSSH 10.0p1
OpenSSH is the premier connectivity tool for remote login with the SSH protocol. It encrypts all traffic to eliminate eavesdropping, connection hijacking, and other attacks. In addition, OpenSSH provides a large suite of secure tunneling capabilities, several authentication methods, and...
Wapiti Web Application Vulnerability Scanner 3.2.4
Wapiti is a web application vulnerability scanner. It will scan the web pages of a deployed web application and will fuzz the URL parameters and forms to find common web vulnerabilities...
Multi-Party Private Set Operations from Predicative Zero-Sharing
Typical protocols in the multi-party private set operations MPSO setting enable m 2 parties to perform certain secure computation on the intersection or union of their private sets, realizing a very limited range of MPSO functionalities. Most works in this field focus on just one or two specific...
Centreon API 19.04 Bruteforcer
Centreon version 19.04 login password bruteforcing tool...
CrushFTP 10 / 11 Authentication Bypass
This proof of concept will exploit the authentication bypass vulnerability in CrushFTP versions 10 before 10.8.4 and 11 before 11.3.1. It will create a new user account with administrative level permissions. It requires the username of an existing user as the target and the default is set to...
FASTRPC_ATTR_KEEP_MAP Use-After-Free
A FASTRPCATTRKEEPMAP logic bug allows fastrpcinternalmunmapfd to concurrently free in-use mappings leading to a use-after-free condition...