LLM vs. SAST: a Technical Analysis on Detecting Coding Bugs of GPT4-Advanced Data Analysis

With the rapid advancements in Natural Language Processing NLP, large language models LLMs like GPT-4 have gained significant traction in diverse applications, including security vulnerability scanning. This paper investigates the efficacy of GPT-4 in identifying software vulnerabilities compared...

Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models

Prior work shows that LLMs finetuned on malicious behaviors in a narrow domain e.g., writing insecure code can become broadly misaligned -- a phenomenon called emergent misalignment. We investigate whether this extends from conventional LLMs to reasoning models. We finetune reasoning models on...

Now More Than Ever, Foundational AI Research and Infrastructure Depends on the Federal Government

Leadership in the field of AI is vital for our nation's economy and security. Maintaining this leadership requires investments by the federal government. The federal investment in foundation AI research is essential for U.S. leadership in the field. Providing accessible AI infrastructure will...

Unlearning-Enhanced Website Fingerprinting Attack: against Backdoor Poisoning in Anonymous Networks

Website Fingerprinting WF is an effective tool for regulating and governing the dark web. However, its performance can be significantly degraded by backdoor poisoning attacks in practical deployments. This paper aims to address the problem of hidden backdoor poisoning attacks faced by Website...

Systems-Theoretic and Data-Driven Security Analysis in ML-enabled Medical Devices

The integration of AI/ML into medical devices is rapidly transforming healthcare by enhancing diagnostic and treatment facilities. However, this advancement also introduces serious cybersecurity risks due to the use of complex and often opaque models, extensive interconnectivity, interoperability...

AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions

The rapid advancement of vision-language models VLMs and their integration into embodied agents have unlocked powerful capabilities for decision-making. However, as these systems are increasingly deployed in real-world environments, they face mounting safety concerns, particularly when responding...

LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops

Multimodal Large Language Models MLLMs have shown great promise but require substantial computational resources during inference. Attackers can exploit this by inducing excessive output, leading to resource exhaustion and service degradation. Prior energy-latency attacks aim to increase generatio...

Real-Time, Low-Latency Surveillance Using Entropy-Based Adaptive Buffering and MobileNetV2 on Edge Devices

This paper describes a high-performance, low-latency video surveillance system designed for resource-constrained environments. We have proposed a formal entropy-based adaptive frame buffering algorithm and integrated that with MobileNetV2 to achieve high throughput with low latency. The system is...

From Permissioned to Proof-of-Stake Consensus

This paper presents the first generic compiler that transforms any permissioned consensus protocol into a proof-of-stake permissionless consensus protocol. For each of the following properties, if the initial permissioned protocol satisfies that property in the partially synchronous setting, the...

Linear and Numerical SDoF Bounds of Active RIS-Assisted MIMO Wiretap Interference Channel

The multiple-input multiple-output MIMO wiretap interference channel IC serves as a canonical model for information-theoretic security, where a multiple-antenna eavesdropper attempts to intercept communications in a two-user MIMO IC system. The secure degrees-of-freedom SDoF of an active...

Optimizing System Latency for Blockchain-Encrypted Edge Computing in Internet of Vehicles

As Internet of Vehicles IoV technology continues to advance, edge computing has become an important tool for assisting vehicles in handling complex tasks. However, the process of offloading tasks to edge servers may expose vehicles to malicious external attacks, resulting in information loss or...

Narrowing the Gap between TEEs Threat Model and Deployment Strategies

Confidential Virtual Machines CVMs provide isolation guarantees for data in use, but their threat model does not include physical level protection and side-channel attacks. Therefore, current deployments rely on trusted cloud providers to host the CVMs' underlying infrastructure. However, TEE...

Characterising Bugs in Jupyter Platform

As a representative literate programming platform, Jupyter is widely adopted by developers, data analysts, and researchers for replication, data sharing, documentation, interactive data visualization, and more. Understanding the bugs in the Jupyter platform is essential for ensuring its...

PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning

Decentralized learning is vulnerable to poison attacks, where malicious clients manipulate local updates to degrade global model performance. Existing defenses mainly detect and filter malicious models, aiming to prevent a limited number of attackers from corrupting the global model. However,...

Toward a Lightweight, Scalable, and Parallel Secure Encryption Engine

The exponential growth of Internet of Things IoT applications has intensified the demand for efficient, high-throughput, and energy-efficient data processing at the edge. Conventional CPU-centric encryption methods suffer from performance bottlenecks and excessive data movement, especially in...

Human-Centred AI in FinTech: Developing a User Experience (UX) Research Point of View (PoV) Playbook

Advancements in Artificial Intelligence AI have significantly transformed the financial industry, enabling the development of more personalized and adaptable financial products and services. This research paper explores various instances where Human-Centred AI HCAI has facilitated these...

Side-Channel Extraction of Dataflow AI Accelerator Hardware Parameters

Dataflow neural network accelerators efficiently process AI tasks on FPGAs, with deployment simplified by ready-to-use frameworks and pre-trained models. However, this convenience makes them vulnerable to malicious actors seeking to reverse engineer valuable Intellectual Property IP through...

Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments

With the growing integration of vision-language models VLMs, mobile agents are now widely used for tasks like UI automation and camera-based user assistance. These agents are often fine-tuned on limited user-generated datasets, leaving them vulnerable to covert threats during the training process...

Understanding Content Moderation Policies and User Experiences in Generative AI Products

While recent research has focused on developing safeguards for generative AI GAI model-level content safety, little is known about how content moderation to prevent malicious content performs for end-users in real-world GAI products. To bridge this gap, we investigated content moderation policies...

Using LLMs for Security Advisory Investigations: How Far Are We?

Large Language Models LLMs are increasingly used in software security, but their trustworthiness in generating accurate vulnerability advisories remains uncertain. This study investigates the ability of ChatGPT to 1 generate plausible security advisories from CVE-IDs, 2 differentiate real from fa...

Offensive Robot Cybersecurity

Offensive Robot Cybersecurity introduces a groundbreaking approach by advocating for offensive security methods empowered by means of automation. It emphasizes the necessity of understanding attackers' tactics and identifying vulnerabilities in advance to develop effective defenses, thereby...

Facility Location Problem under Local Differential Privacy without Super-set Assumption

In this paper, we introduce an adaptation of the facility location problem and analyze it within the framework of local differential privacy LDP. Under this model, we ensure the privacy of client presence at specific locations...

Watermarking LLM-Generated Datasets in Downstream Tasks

Large Language Models LLMs have experienced rapid advancements, with applications spanning a wide range of fields, including sentiment classification, review generation, and question answering. Due to their efficiency and versatility, researchers and companies increasingly employ LLM-generated da...

A Locally Differential Private Coding-Assisted Succinct Histogram Protocol

A succinct histogram captures frequent items and their frequencies across clients and has become increasingly important for large-scale, privacy-sensitive machine learning applications. To develop a rigorous framework to guarantee privacy for the succinct histogram problem, local differential...

AI Safety Vs. AI Security: Demystifying the Distinction and Boundaries

Artificial Intelligence AI is rapidly being integrated into critical systems across various domains, from healthcare to autonomous vehicles. While its integration brings immense benefits, it also introduces significant risks, including those arising from AI misuse. Within the discourse on managin...

ImpReSS: Implicit Recommender System for Support Conversations

Following recent advancements in large language models LLMs, LLM-based chatbots have transformed customer support by automating interactions and providing consistent, scalable service. While LLM-based conversational recommender systems CRSs have attracted attention for their ability to enhance th...

Private Continual Counting of Unbounded Streams

We study the problem of differentially private continual counting in the unbounded setting where the input size $n$ is not known in advance. Current state-of-the-art algorithms based on optimal instantiations of the matrix mechanism cannot be directly applied here because their privacy guarantees...

Dual Protection Ring: User Profiling Via Differential Privacy and Service Dissemination through Private Information Retrieval

User profiling is crucial in providing personalised services, as it relies on analyzing user behaviour and preferences to deliver targeted services. This approach enhances user experience and promotes heightened engagement. Nevertheless, user profiling also gives rise to noteworthy privacy...

deepSURF: Detecting Memory Safety Vulnerabilities in Rust through Fuzzing LLM-Augmented Harnesses

Although Rust ensures memory safety by default, it also permits the use of unsafe code, which can introduce memory safety vulnerabilities if misused. Unfortunately, existing tools for detecting memory bugs in Rust typically exhibit limited detection capabilities, inadequately handle Rust-specific...

Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values

Agentic AI systems, possessing capabilities for autonomous planning and action, exhibit immense potential across diverse domains. However, their practical deployment is significantly hampered by challenges in aligning their behavior with varied human values, complex safety requirements, and...

Movable Antennas Meet Low-Altitude Wireless Networks: Fundamentals, Opportunities, and Future Directions

With the rapid development of low-altitude applications, there is an increasing demand for low-altitude wireless networks LAWNs to simultaneously achieve high-rate communication, precise sensing, and reliable control in the low-altitude airspace. In this paper, we first present a typical system...

SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis

The integration of open-source third-party library dependencies in Java development introduces significant security risks when these libraries contain known vulnerabilities. Existing Software Composition Analysis SCA tools struggle to effectively detect vulnerable API usage from these libraries d...

LASA: Enhancing SoC Security Verification with LLM-Aided Property Generation

Ensuring the security of modern System-on-Chip SoC designs poses significant challenges due to increasing complexity and distributed assets across the intellectual property IP blocks. Formal property verification FPV provides the capability to model and validate design behaviors through security...

From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMs

Large Language Models LLMs are set to reshape cybersecurity by augmenting red and blue team operations. Red teams can exploit LLMs to plan attacks, craft phishing content, simulate adversaries, and generate exploit code. Conversely, blue teams may deploy them for threat intelligence synthesis, ro...

Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference

Differential privacy DP auditing aims to provide empirical lower bounds on the privacy guarantees of DP mechanisms like DP-SGD. While some existing techniques require many training runs that are prohibitively costly, recent work introduces one-run auditing approaches that effectively audit DP-SGD...

Certified Randomness from Quantum Speed Limits

Quantum speed limits are usually regarded as fundamental restrictions, constraining the amount of computation that can be achieved within some given time and energy. Complementary to this intuition, here we show that these limitations are also of operational value: they enable the secure generati...

Secure Time-Modulated Intelligent Reflecting Surface via Generative Flow Networks

We propose a novel directional modulation DM design for OFDM transmitters aided by a time-modulated intelligent reflecting surface TM-IRS. The TM-IRS is configured to preserve the integrity of transmitted signals toward multiple legitimate users while scrambling the signal in all other directions...

Detecting Hard-Coded Credentials in Software Repositories Via LLMs

Software developers frequently hard-code credentials such as passwords, generic secrets, private keys, and generic tokens in software repositories, even though it is strictly advised against due to the severe threat to the security of the software. These credentials create attack surfaces...

Don't Throw the Baby out with the Bathwater: How and Why Deep Learning for ARC

The Abstraction and Reasoning Corpus ARC-AGI presents a formidable challenge for AI systems. Despite the typically low performance on ARC, the deep learning paradigm remains the most effective known strategy for generating skillful state-of-the-art neural networks NN across varied modalities and...

Navigating the Growing Field of Research on AI for Software Testing

In industry, software testing is the primary method to verify and validate the functionality, performance, security, usability, and so on, of software-based systems. Test automation has gained increasing attention in industry over the last decade, following decades of intense research into test...

A Comprehensive Survey on Underwater Acoustic Target Positioning and Tracking: Progress, Challenges, and Perspectives

Underwater target tracking technology plays a pivotal role in marine resource exploration, environmental monitoring, and national defense security. Given that acoustic waves represent an effective medium for long-distance transmission in aquatic environments, underwater acoustic target tracking h...

LLM-Powered Intent-Based Categorization of Phishing Emails

Phishing attacks remain a significant threat to modern cybersecurity, as they successfully deceive both humans and the defense mechanisms intended to protect them. Traditional detection systems primarily focus on email metadata that users cannot see in their inboxes. Additionally, these systems...

Anonymous Authentication using Attribute-based Encryption

In today's digital age, personal data is constantly at risk of compromise. Attribute-Based Encryption ABE has emerged as a promising approach to privacy-preserving data protection. This paper proposes an anonymous authentication mechanism based on ABE, which allows users to authenticate without...

Domain Adaptation for Image Classification of Defects in Semiconductor Manufacturing

In the semiconductor sector, due to high demand but also strong and increasing competition, time to market and quality are key factors in securing significant market share in various application areas. Thanks to the success of deep learning methods in recent years in the computer vision domain,...

Agent Capability Negotiation and Binding Protocol (ACNBP)

As multi-agent systems evolve to encompass increasingly diverse and specialized agents, the challenge of enabling effective collaboration between heterogeneous agents has become paramount, with traditional agent communication protocols often assuming homogeneous environments or predefined...

CEGA: a Cost-Effective Approach for Graph-Based Model Extraction and Acquisition

Graph Neural Networks GNNs have demonstrated remarkable utility across diverse applications, and their growing complexity has made Machine Learning as a Service MLaaS a viable platform for scalable deployment. However, this accessibility also exposes GNN to serious security threats, most notably...

ReDASH: Fast and efficient Scaling in Arithmetic Garbled Circuits for Secure Outsourced Inference

Whitepaper called ReDASH: Fast and efficient Scaling in Arithmetic Garbled Circuits for Secure Outsourced Inference...

Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and Explainability

Phishing attacks remain one of the most prevalent and persistent cybersecurity threat with attackers continuously evolving and intensifying tactics to evade the general detection system. Despite significant advances in artificial intelligence and machine learning, faithfully reproducing the...

Quantum Enhanced Entropy Pool for Cryptographic Applications and Proofs

This paper investigates the integration of quantum randomness into Verifiable Random Functions VRFs using the Ed25519 elliptic curve to strengthen cryptographic security. By replacing traditional pseudorandom number generators with quantum entropy sources, we assess the impact on key security and...

Q-AIM: a Unified Portable Workflow for Seamless Integration of Quantum Resources

Quantum computing QC holds the potential to solve classically intractable problems. Although there has been significant progress towards the availability of quantum hardware, a software infrastructure to integrate them is still missing. We present Q-AIM Quantum Access Infrastructure Management to...