5582 matches found
Mitigating the Structural Bias in Graph Adversarial Defenses
In recent years, graph neural networks GNNs have shown great potential in addressing various graph structure-related downstream tasks. However, recent studies have found that current GNNs are susceptible to malicious adversarial attacks. Given the inevitable presence of adversarial attacks in the...
CachePrune: Neural-Based Attribution Defense against Indirect Prompt Injection Attacks
Large Language Models LLMs are identified as being susceptible to indirect prompt injection attack, where the model undesirably deviates from user-provided instructions by executing tasks injected in the prompt context. This vulnerability stems from LLMs' inability to distinguish between data and...
SFIBA: Spatial-Based Full-Target Invisible Backdoor Attacks
Multi-target backdoor attacks pose significant security threats to deep neural networks, as they can preset multiple target classes through a single backdoor injection. This allows attackers to control the model to misclassify poisoned samples with triggers into any desired target class during...
Robustness Via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
Large language models LLMs have demonstrated impressive performance and have come to dominate the field of natural language processing NLP across various tasks. However, due to their strong instruction-following capabilities and inability to distinguish between instructions and data content, LLMs...
CVE-2024-10635
Enterprise Protection contains an improper input validation vulnerability in attachment defense that allows an unauthenticated remote attacker to bypass attachment scanning security policy by sending a malicious S/MIME attachment with an opaque signature. When opened by a recipient in a downstrea...
CVE-2024-10635
Enterprise Protection contains an improper input validation vulnerability in attachment defense that allows an unauthenticated remote attacker to bypass attachment scanning security policy by sending a malicious S/MIME attachment with an opaque signature. When opened by a recipient in a downstrea...
CVE-2024-10635 Enterprise Protection S/MIME Opaque Signature Attachment Scanning Bypass
Enterprise Protection contains an improper input validation vulnerability in attachment defense that allows an unauthenticated remote attacker to bypass attachment scanning security policy by sending a malicious S/MIME attachment with an opaque signature. When opened by a recipient in a downstrea...
A Cryptographic Perspective on Mitigation Vs. Detection in Machine Learning
In this paper, we initiate a cryptographically inspired theoretical study of detection versus mitigation of adversarial inputs produced by attackers of Machine Learning algorithms during inference time. We formally define defense by detection DbD and defense by mitigation DbM. Our definitions com...
Proofpoint Enterprise Protection 安全漏洞
Proofpoint Enterprise Protection is an application from Proofpoint USA, Inc. provides functionality to protect e-mail. A security vulnerability exists in Proofpoint Enterprise Protection versions prior to 8.22.0 that stems from improper input validation in Attachment Defense, which could result i...
PT-2025-18114 · Unknown · Enterprise Protection
Name of the Vulnerable Software and Affected Versions: Enterprise Protection affected versions not specified Description: The issue is related to an improper input validation vulnerability in the attachment defense of Enterprise Protection. This vulnerability allows an unauthenticated remote...
A Case Study on the Use of Representativeness Bias As a Defense against Adversarial Cyber Threats
Cyberspace is an ever-evolving battleground involving adversaries seeking to circumvent existing safeguards and defenders aiming to stay one step ahead by predicting and mitigating the next threat. Existing mitigation strategies have focused primarily on solutions that consider software or hardwa...
SONNI: Secure Oblivious Neural Network Inference
In the standard privacy-preserving Machine learning as-a-service MLaaS model, the client encrypts data using homomorphic encryption and uploads it to a server for computation. The result is then sent back to the client for decryption. It has become more and more common for the computation to be...
Wordfence Intelligence Weekly WordPress Vulnerability Report (April 14, 2025 to April 20, 2025)
In case you missed it, Wordfence just published itsannual WordPress security report for 2024. Read it now to learn more about the evolving risk landscape of WordPress so you can keep your sites protected in 2025 and beyond. Last week, there were 259 vulnerabilities disclosed in 222 WordPress...
ALBEDO Telecom Net.Time - PTP/NTP clock
RISK EVALUATION Successful exploitation of this vulnerability could allow an attacker to transmit passwords over unencrypted connections, resulting in the product becoming vulnerable to interception. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of...
Vestel AC Charger
RISK EVALUATION Successful exploitation of this vulnerability could allow an attacker access to sensitive information, such as credentials which could subsequently enable them to cause a denial of service or partial loss of integrity of the charger. 2. RECOMMENDED PRACTICES CISA reminds...
Johnson Controls Software House iSTAR Configuration Utility (ICU) Tool
RISK EVALUATION Successful exploitation of this vulnerability may allow an attacker to execute arbitrary code. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of this vulnerability, such as: Minimize network exposure for all control...
Biting the CHERI Bullet: Blockers, Enablers and Security Implications of CHERI in Defence
There is growing interest in securing the hardware foundations software stacks build upon. However, before making any investment decision, software and hardware supply chain stakeholders require evidence from realistic, multiple long-term studies of adoption. We present results from a 12 month...
Iran-Linked Hackers Target Israel with MURKYTOUR Malware via Fake Job Campaign
The Iran-nexus threat actor known as UNC2428 has been observed delivering a backdoor known as MURKYTOUR as part of a job-themed social engineering campaign aimed at Israel in October 2024. Google-owned Mandiant described UNC2428 as a threat actor aligned with Iran that engages in cyber...
VulnCheck KEV: CVE-2020-3529
A vulnerability in the SSL VPN negotiation process for Cisco Adaptive Security Appliance ASA Software and Cisco Firepower Threat Defense FTD Software could allow an unauthenticated, remote attacker to cause a reload of an affected device, resulting in a denial of service DoS condition...
