CVE-2024-39350

A vulnerability regarding authentication bypass by spoofing is found in the RTSP functionality. This allows man-in-the-middle attackers to obtain privileges without consent via unspecified vectors. The following models with Synology Camera Firmware versions before 1.0.7-0298 may be affected: BC50...

The Echo Chamber Multi-Turn LLM Jailbreak

The availability of Large Language Models LLMs has led to a new generation of powerful chatbots that can be developed at relatively low cost. As companies deploy these tools, security challenges need to be addressed to prevent financial loss and reputational damage. A key security challenge is...

CVE-2019-25291

INIM Electronics Smartliving SmartLAN/G/SI =6.x contains hard-coded credentials in its Linux distribution image that cannot be changed through normal device operations. Attackers can exploit these persistent credentials to log in and gain unauthorized system access across multiple SmartLiving...

CurricuLLM: Designing Personalized and Workforce-Aligned Cybersecurity Curricula Using Fine-Tuned LLMs

The cybersecurity landscape is constantly evolving, driven by increased digitalization and new cybersecurity threats. Cybersecurity programs often fail to equip graduates with skills demanded by the workforce, particularly concerning recent developments in cybersecurity, as curriculum design is...

Multi-Turn Jailbreaking Attack in Multi-Modal Large Language Models

In recent years, the security vulnerabilities of Multi-modal Large Language Models MLLMs have become a serious concern in the Generative Artificial Intelligence GenAI research. These highly intelligent models, capable of performing multi-modal tasks with high accuracy, are also severely susceptib...

Memory Poisoning Attack and Defense on Memory Based LLM-Agents

Large language model agents equipped with persistent memory are vulnerable to memory poisoning attacks, where adversaries inject malicious instructions through query only interactions that corrupt the agents long term memory and influence future responses. Recent work demonstrated that the MINJA...

CVE-2019-25291 INIM Electronics Smartliving SmartLAN/G/SI <=6.x Hard-coded Credentials Vulnerability

INIM Electronics Smartliving SmartLAN/G/SI =6.x contains hard-coded credentials in its Linux distribution image that cannot be changed through normal device operations. Attackers can exploit these persistent credentials to log in and gain unauthorized system access across multiple SmartLiving...

CVE-2019-25291

INIM Electronics Smartliving SmartLAN/G/SI =6.x contains hard-coded credentials in its Linux distribution image that cannot be changed through normal device operations. Attackers can exploit these persistent credentials to log in and gain unauthorized system access across multiple SmartLiving...

CVE-2019-25291

CVE-2019-25291 affects INIM Electronics Smartliving SmartLAN/G/SI versions 6.x and earlier, where hard-coded credentials are baked into the Linux distribution image and cannot be changed via normal device operations. This enables attackers to log in and gain unauthorized system access across mult...

CVE-2026-0625

Multiple D-Link DSL/DIR/DNS devices contain an authentication bypass and improper access control vulnerability in the dnscfg.cgi endpoint that allows an unauthenticated attacker to access DNS configuration functionality. By directly requesting this endpoint, an attacker can modify the device’s DN...

Ongoing Attacks Exploiting Critical RCE Vulnerability in Legacy D-Link DSL Routers

A newly discovered critical security flaw in legacy D-Link DSL gateway routers has come under active exploitation in the wild. The vulnerability, tracked as CVE-2026-0625 CVSS score: 9.3, concerns a case of command injection in the "dnscfg.cgi" endpoint that arises as a result of improper...

Efacec QC 安全漏洞

Efacec QC is a series of electric vehicle charging posts from Efacec Portugal. A security vulnerability exists in the Efacec QC 60/90/120 that stems from the unencrypted MQTT communication protocol, which could lead an attacker to write data to the server subject controlling the MQTT communicatio...

HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense

Jailbreak attacks pose significant threats to large language models LLMs, enabling attackers to bypass safeguards. However, existing reactive defense approaches struggle to keep up with the rapidly evolving multi-turn jailbreaks, where attackers continuously deepen their attacks to exploit...

Jailbreaking LLMs and VLMs: Mechanisms, Evaluation, and Unified Defense

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models LLMs and Vision-Language Models VLMs, emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training data, linguistic ambiguity, and generative uncertainty. It...

RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models

As large language models LLMs become integral to safety-critical applications, ensuring their robustness against adversarial prompts is paramount. However, existing red teaming datasets suffer from inconsistent risk categorizations, limited domain coverage, and outdated evaluations, hindering...

A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-Case Prototypes

Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these systems enable continuous, autonomous workflows in real-world...

TFSMLayer bypasses `safe_mode=True`, allowing attacker-controlled code execution during model inference

Summary TFSMLayer allows loading attacker-controlled TensorFlow SavedModels when deserializing a .keras model, even when safemode=True the default. While TensorFlow does not execute SavedModel functions during load, the attacker-controlled graph is registered during deserialization and executes...

CVE-2025-52516

An issue was discovered in the Camera in Samsung Mobile Processor and Wearable Processor Exynos 1330, 1380, 1480, 2400, 1580, 2500. An invalid kernel address dereference in the issimian device driver leads to a denial of service...

SAMSUNG多款产品 安全漏洞

SAMSUNG Wearable Processor and others are products of the South Korean company Samsung.SAMSUNG Wearable Processor is a series of wearable processors.SAMSUNG Exynos 990 is a mobile processor.SAMSUNG Exynos 850 is a mobile processor. SAMSUNG Exynos 850 is a mobile processor. A security vulnerabilit...

Quantum AI for Cybersecurity: A Hybrid Quantum-Classical Models for Attack Path Analysis

Modern cyberattacks are increasingly complex, posing significant challenges to classical machine learning methods, particularly when labeled data is limited and feature interactions are highly non-linear. In this study we investigates the potential of hybrid quantum-classical learning to enhance...