GPT-4o-mini Falls for Psychological Manipulation

Interesting experiment: To design their experiment, the University of Pennsylvania researchers tested 2024's GPT-4o-mini model on two requests that it should ideally refuse: calling the user a jerk and giving directions for how to synthesize lidocaine. The researchers created experimental prompts...

Linux Distros Unpatched Vulnerability : CVE-2021-32274

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - An issue was discovered in faad2 through 2.10.0. A heap-buffer-overflow exists in the function sbrqmfsynthesis64 located in sbrqmf.c. It allows an attacker to...

Locus: Agentic Predicate Synthesis for Directed Fuzzing

Directed fuzzing aims to find program inputs that lead to specified target program states. It has broad applications, such as debugging system crashes, confirming reported bugs, and generating exploits for potential vulnerabilities. This task is inherently challenging because target states are...

GPT-SoVITS-WebUI 命令注入漏洞

GPT-SoVITS-WebUI is a TTS training model. A command injection vulnerability exists in the GPT-SoVITS-WebUI opendenoise function, which can be exploited by an attacker to execute arbitrary commands on the system...

ELFuzz: Efficient Input Generation Via LLM-Driven Synthesis over Fuzzer Space

Generation-based fuzzing produces appropriate testing cases according to specifications of input grammars and semantic constraints to test systems and software. However, these specifications require significant manual efforts to construct. This paper proposes a new approach, ELFuzz Evolution...

PoSyn: Secure Power Side-Channel Aware Synthesis

Power Side-Channel PSC attacks exploit power consumption patterns to extract sensitive information, posing risks to cryptographic operations crucial for secure systems. Traditional countermeasures, such as masking, face challenges including complex integration during synthesis, substantial area...

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges

Large Language Models LLMs still struggle with the structured reasoning and tool-assisted computation needed for problem solving in cybersecurity applications. In this work, we introduce "random-crypto", a cryptographic Capture-the-Flag CTF challenge generator framework that we use to fine-tune a...

USB: a Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

Despite their remarkable achievements and widespread adoption, Multimodal Large Language Models MLLMs have revealed significant security vulnerabilities, highlighting the urgent need for robust safety evaluation benchmarks. Existing MLLM safety benchmarks, however, fall short in terms of data...

CVE-2024-23907

Uncontrolled search path in some IntelR High Level Synthesis Compiler software before version 23.4 may allow an authenticated user to potentially enable escalation of privilege via local access...

CVE-2024-38467

Shenzhen Guoxin Synthesis image system before 8.3.0 allows unauthorized user information retrieval via the queryUser API...

CVE-2024-31407

Uncontrolled search path in some IntelR High Level Synthesis Compiler software for IntelR QuartusR Prime Pro Edition Software before version 24.1 may allow an authenticated user to potentially enable escalation of privilege via local access...

Compile-Time Fully Homomorphic Encryption of Vectors: Eliminating Online Encryption Via Algebraic Basis Synthesis

Whitepaper called Compile-Time Fully Homomorphic Encryption Of Vectors: Eliminating Online Encryption Via Algebraic Basis Synthesis...

CRYPTONITE: Scalable Accelerator Design for Cryptographic Primitives and Algorithms

Cryptographic primitives, consisting of repetitive operations with different inputs, are typically implemented using straight-line C code due to traditional execution on CPUs. Computing these primitives is necessary for secure communication; thus, dedicated hardware accelerators are required in...

SynFuzz: Leveraging Fuzzing of Netlist to Detect Synthesis Bugs

In the evolving landscape of integrated circuit IC design, the increasing complexity of modern processors and intellectual property IP cores has introduced new challenges in ensuring design correctness and security. The recent advancements in hardware fuzzing techniques have shown their efficacy ...

SOLIDO: a Robust Watermarking Method for Speech Synthesis Via Low-Rank Adaptation

Whitepaper called SOLIDO: A Robust Watermarking Method For Speech Synthesis Via Low-Rank Adaptation...

Complexity of Post-Quantum Cryptography in Embedded Systems and Its Optimization Strategies

With the rapid advancements in quantum computing, traditional cryptographic schemes like Rivest-Shamir-Adleman RSA and elliptic curve cryptography ECC are becoming vulnerable, necessitating the development of quantum-resistant algorithms. The National Institute of Standards and Technology NIST ha...

Benchmarking Differentially Private Tabular Data Synthesis

Differentially private DP tabular data synthesis generates artificial data that preserves the statistical properties of private data while safeguarding individual privacy. The emergence of diverse algorithms in recent years has introduced challenges in practical applications, such as inconsistent...

On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks

Augmented Reality AR and Multimodal Large Language Models LLMs are rapidly evolving, providing unprecedented capabilities for human-computer interaction. However, their integration introduces a new attack surface for social engineering. In this paper, we systematically investigate the feasibility...

Important: thunderbird

Issue Overview: Requests initiated through reader mode did not properly omit cookies with a SameSite attribute. This vulnerability affects Thunderbird 91.9, Firefox ESR 91.9, and Firefox 100. CVE-2022-29912 The parent process would not properly check whether the Speech Synthesis feature is...

Important: thunderbird

Issue Overview: Requests initiated through reader mode did not properly omit cookies with a SameSite attribute. This vulnerability affects Thunderbird 91.9, Firefox ESR 91.9, and Firefox 100. CVE-2022-29912 The parent process would not properly check whether the Speech Synthesis feature is...