When and Where Do Data Poisons Attack Textual Inversion?

Poisoning attacks pose significant challenges to the robustness of diffusion models DMs. In this paper, we systematically analyze when and where poisoning attacks textual inversion TI, a widely used personalization technique for DMs. We first introduce Semantic Sensitivity Maps, a novel method fo...

Entangled Threats: a Unified Kill Chain Model for Quantum Machine Learning Security

Quantum Machine Learning QML systems inherit vulnerabilities from classical machine learning while introducing new attack surfaces rooted in the physical and algorithmic layers of quantum computing. Despite a growing body of research on individual attack vectors - ranging from adversarial poisoni...

Delta Electronics DTM Soft

RISK EVALUATION Successful exploitation of this vulnerability could allow an attacker to encrypt files referencing the application in order to extract information. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of this vulnerability,...

Can Large Language Models Improve Phishing Defense? A Large-Scale Controlled Experiment on Warning Dialogue Explanations

Phishing has become a prominent risk in modern cybersecurity, often used to bypass technological defences by exploiting predictable human behaviour. Warning dialogues are a standard mitigation measure, but the lack of explanatory clarity and static content limits their effectiveness. In this pape...

Defending against Prompt Injection with a Few DefensiveTokens

When large language model LLM systems interact with external data to perform complex tasks, a new attack, namely prompt injection, becomes a significant threat. By injecting instructions into the data accessed by the system, the attacker is able to override the initial user task with an arbitrary...

May I Have Your Attention? Breaking Fine-Tuning Based Prompt Injection Defenses Using Architecture-Aware Attacks

A popular class of defenses against prompt injection attacks on large language models LLMs relies on fine-tuning the model to separate instructions and data, so that the LLM does not follow instructions that might be present with data. There are several academic systems and production-level...

Hedge Funds on a Swamp: Analyzing Patterns, Vulnerabilities, and Defense Measures in Blockchain Bridges [Experiment, Analysis and Benchmark]

Blockchain bridges have become essential infrastructure for enabling interoperability across different blockchain networks, with more than $24B monthly bridge transaction volume. However, their growing adoption has been accompanied by a disproportionate rise in security breaches, making them the...

PT-2025-29180 · Emerson · Valvelink

Name of the Vulnerable Software and Affected Versions: Emerson ValveLink products affected versions not specified Description: Emerson ValveLink products do not use or incorrectly use a protection mechanism, providing insufficient defense against directed attacks. Recommendations: At the moment,...

Understanding Malware Propagation Dynamics through Scientific Machine Learning

Accurately modeling malware propagation is essential for designing effective cybersecurity defenses, particularly against adaptive threats that evolve in real time. While traditional epidemiological models and recent neural approaches offer useful foundations, they often fail to fully capture the...

Pakistan’s Transparent Tribe Hits Indian Defence with Linux Malware

Pakistan’s APT36 Transparent Tribe uses phishing and Linux malware to target Indian defence systems running BOSS Linux says Cyfirma...

CAVGAN: Unifying Jailbreak and Defense of LLMs Via Generative Adversarial Attacks on Their Internal Representations

Security alignment enables the Large Language Model LLM to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM jailbreak attacks and defenses. We analyze the security protection...

Learn how to build an AI-powered, unified SOC in new Microsoft e-book

The sheer volume of cyberattacks continues to increase at a breathtaking scale worldwide, with customers facing more than 600 million cybercriminal and nation-state attacks every day.1 To stem the growing tide of malicious cyber activity takes a commitment from all of us—individuals from operatio...

CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation

Deep Neural Networks DNNs are susceptible to backdoor attacks, where adversaries poison training data to implant backdoor into the victim model. Current backdoor defenses on poisoned data often suffer from high computational costs or low effectiveness against advanced attacks like clean-label and...

Addressing the Devastating Effects of Single-Task Data Poisoning in Exemplar-Free Continual Learning

Our research addresses the overlooked security concerns related to data poisoning in continual learning CL. Data poisoning - the intentional manipulation of training data to affect the predictions of machine learning models - was recently shown to be a threat to CL training stability. While...

LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing

The proliferation of Low-Rank Adaptation LoRA models has democratized personalized text-to-image generation, enabling users to share lightweight models e.g., personal portraits on platforms like Civitai and Liblib. However, this "share-and-play" ecosystem introduces critical risks: benign LoRAs c...

China Linked Houken Hackers Breach French Systems with Ivanti Zero Days

ANSSI report details the Chinese UNC5174 linked Houken cyberattack using Ivanti zero-days CVE-2024-8190, 8963, 9380 against the French government, defence and finance sector...

ABB RMC-100 (Update A)

RISK EVALUATION Successful exploitation of these vulnerabilities could allow an attacker to gain unauthenticated access to the MQTT configuration data, cause a denial-of-service condition on the MQTT configuration web server REST interface, or decrypt encrypted MQTT broker credentials. 2...

Agentic AI Is Here — and It’s Shaping the Future of Bot Defense

...

U.S. Agencies Warn of Rising Iranian Cyber Attacks on Defense, OT Networks, and Critical Infrastructure

U.S. cybersecurity and intelligence agencies have issued a joint advisory warning of potential cyber attacks from Iranian state-sponsored or affiliated threat actors. "Over the past several months, there has been increasing activity from hacktivists and Iranian government-affiliated actors, which...

CVE-2025-5878

A vulnerability was found in ESAPI esapi-java-legacy and classified as problematic. This issue affects the interface Encoder.encodeForSQL of the SQL Injection Defense. An attack leads to an improper neutralization of special elements. The attack may be initiated remotely and an exploit has been...