Investigating Cybersecurity Incidents Using Large Language Models in Latest-Generation Wireless Networks

The purpose of research: Detection of cybersecurity incidents and analysis of decision support and assessment of the effectiveness of measures to counter information security threats based on modern generative models. The methods of research: Emulation of signal propagation data in MIMO systems,...

AI Data Poisoning

Cloudflare has a new feature--available to free users as well--that uses AI to generate random pages to feed to AI web crawlers: Instead of simply blocking bots, Cloudflare's new system lures them into a "maze" of realistic-looking but irrelevant pages, wasting the crawler's computing resources...

CVE-2023-50943

Apache Airflow, versions before 2.8.1, have a vulnerability that allows a potential attacker to poison the XCom data by bypassing the protection of "enablexcompickling=False" configuration setting resulting in poisoned data after XCom deserialization. This vulnerability is considered low since it...

MAI-2024-0061

This vulnerability involves a data poisoning attack targeting Retrieval-Augmented Generation RAG systems. The attack manipulates the retriever component by injecting a compromised document into the dataset utilized by the embedding model. The injected document is altered to contain inaccurate and...

Securing AI Development in the Cloud: Navigating the Risks and Opportunities

AI-TRiSM - Trust, Risk and Security Management in the Age of AI Co-authored by Lara Sunday and Pojan Shahrivar As artificial intelligence AI and machine learning ML technologies continue to advance and proliferate, organizations across industries are investing heavily in these transformative...

CVE-2024-5185

The EmbedAI application is susceptible to security issues that enable Data Poisoning attacks. This weakness could result in the application becoming compromised, leading to unauthorized entries or data poisoning attacks, which are delivered by a CSRF vulnerability due to the absence of a secure...

CVE-2024-5185 Data Poisoning in EmbedAI

The EmbedAI application is susceptible to security issues that enable Data Poisoning attacks. This weakness could result in the application becoming compromised, leading to unauthorized entries or data poisoning attacks, which are delivered by a CSRF vulnerability due to the absence of a secure...

CVE-2024-5185

CVE-2024-5185 concerns the EmbedAI application, where a CSRF weakness resulting from the absence of secure session management and weak CORS policies enables data poisoning. An attacker can lure a user to a malicious page that triggers the CSRF flaw, causing the user to upload and integrate incorr...

CVE-2024-5185 Data Poisoning in EmbedAI

The EmbedAI application is susceptible to security issues that enable Data Poisoning attacks. This weakness could result in the application becoming compromised, leading to unauthorized entries or data poisoning attacks, which are delivered by a CSRF vulnerability due to the absence of a secure...

PrivateGPT 安全漏洞

PrivateGPT is an AI project. PrivateGPT has a security vulnerability that stems from a lack of secure session management implementation and a weak CORS policy, resulting in a cross-site request forgery CSRF vulnerability. An attacker could use this vulnerability to trigger a data poisoning attack...

PT-2024-34978

Name of the Vulnerable Software and Affected Versions EmbedAI affected versions not specified Description The EmbedAI application is susceptible to security issues that enable Data Poisoning attacks due to the absence of a secure session management implementation and weak CORS policies weakness...

CVE-2024-5185: Cross-Site Request Forgery (CSRF)

The EmbedAI application is susceptible to security issues that enable Data Poisoning attacks. This weakness could result in the application becoming compromised, leading to unauthorized entries or data poisoning attacks, which are delivered by a CSRF vulnerability due to the absence of a secure...

BIT-AIRFLOW-2023-50943 Apache Airflow: Potential pickle deserialization vulnerability in XComs

Apache Airflow, versions before 2.8.1, have a vulnerability that allows a potential attacker to poison the XCom data by bypassing the protection of "enablexcompickling=False" configuration setting resulting in poisoned data after XCom deserialization. This vulnerability is considered low since it...

MAI-2024-0065

The ImgTrojan attack represents a sophisticated data poisoning strategy targeting Vision-Language Models VLMs. This method enables adversaries to circumvent built-in safety protocols by introducing a minimal number of maliciously designed image-caption pairs into the training dataset. These...

HackerOne: LLM03: Training Data Poisoning via ASCII decoding

Vulnerability description not provided...

CVE-2023-50943

Apache Airflow, versions before 2.8.1, have a vulnerability that allows a potential attacker to poison the XCom data by bypassing the protection of "enablexcompickling=False" configuration setting resulting in poisoned data after XCom deserialization. This vulnerability is considered low since it...

PYSEC-2024-13

Apache Airflow, versions before 2.8.1, have a vulnerability that allows a potential attacker to poison the XCom data by bypassing the protection of "enablexcompickling=False" configuration setting resulting in poisoned data after XCom deserialization. This vulnerability is considered low since it...

PYSEC-2024-13

Apache Airflow, versions before 2.8.1, have a vulnerability that allows a potential attacker to poison the XCom data by bypassing the protection of "enablexcompickling=False" configuration setting resulting in poisoned data after XCom deserialization. This vulnerability is considered low since it...

CVE-2023-50943

Apache Airflow, versions before 2.8.1, have a vulnerability that allows a potential attacker to poison the XCom data by bypassing the protection of "enablexcompickling=False" configuration setting resulting in poisoned data after XCom deserialization. This vulnerability is considered low since it...

CVE-2023-50943 Apache Airflow: Potential pickle deserialization vulnerability in XComs

Apache Airflow, versions before 2.8.1, have a vulnerability that allows a potential attacker to poison the XCom data by bypassing the protection of "enablexcompickling=False" configuration setting resulting in poisoned data after XCom deserialization. This vulnerability is considered low since it...