CVE-2023-38294

Certain software builds for the Itel Vision 3 Turbo Android device contain a vulnerable pre-installed app with a package name of com.transsion.autotest.factory versionCode='7', versionName='1.8.02203101027' that allows local third-party apps to execute arbitrary shell commands in its context syst...

CVE-2023-47882

The Kami Vision YI IoT com.yunyi.smartcamera application through 4.1.920231127 for Android allows a remote attacker to execute arbitrary JavaScript code via an implicit intent to the com.ants360.yicamera.activity.WebViewActivity component...

CVE-2023-39734

The leakage of the client secret in VISION MEAT WORKS TrackDiner10/10mc Line v13.6.1 allows attackers to obtain the channel access token and send crafted broadcast messages...

CVE-2023-39051

An information leak in VISION MEAT WORKS Track Diner 10/10mbl v13.6.1 allows attackers to obtain the channel access token and send crafted messages...

CVE-2023-21431

Improper input validation in Bixby Vision prior to version 3.7.70.17 allows attacker to access data of Bixby Vision...

CVE-2022-33281

Memory corruption due to improper validation of array index in computer vision while testing EVA kernel without sending any frames...

CVE-2022-24957

DHC Vision eQMS through 5.4.8.322 has Persistent XSS due to insufficient encoding of untrusted input/output. To exploit the vulnerability, the attacker has to create or edit a new information object and use the XSS payload as the name. Any user that opens the object's version or history tab will ...

CVE-2022-24003

Exposure of Sensitive Information vulnerability in Bixby Vision prior to version 3.7.50.6 allows attackers to access internal data of Bixby Vision via unprotected intent...

CVE-2022-35890

An issue was discovered in Inductive Automation Ignition before 7.9.20 and 8.x before 8.1.17. Designer and Vision Client Session IDs are mishandled. An attacker can determine which session IDs were generated in the past and then hijack sessions assigned to these IDs via Randy...

CVE-2021-30046

VIGRA Computer Vision Library Version-1-11-1 contains a segmentation fault vulnerability in the impex.hxx readimageband function, in which a crafted file can cause a denial of service...

CVE-2021-36134

Out of bounds write vulnerability in the JPEG parsing code of Netop Vision Pro up to and including 9.7.2 allows an adjacent unauthenticated attacker to write to arbitrary memory potentially leading to a Denial of Service DoS...

CVE-2021-25467

Assuming system privilege is gained, possible buffer overflow vulnerabilities in the Vision DSP kernel driver prior to SMR Oct-2021 Release 1 allows privilege escalation to Root by hijacking loaded library...

CVE-2020-9529

Firmware developed by Shenzhen Hichip Vision Technology V6 through V20, as used by many different vendors in millions of Internet of Things devices, suffers from a privilege escalation vulnerability that allows attackers on the local network to reset the device's administrator password. This...

CVE-2020-6848

Axper Vision II 4 devices allow XSS via the DEVICENAME aka Device Name parameter to the configWebParams.cgi URI...

CVE-2020-25167

OSIsoft PI Vision 2020 versions prior to 3.5.0 could disclose information to a user with insufficient privileges for an AF attribute...

CVE-2019-18271

OSIsoft PI Vision, All versions of PI Vision prior to 2019. The affected product is vulnerable to a cross-site request forgery that may be introduced on the PI Vision administration site...

CVE-2013-0139

The Arecont Vision AV1355DN MegaDome camera allows remote attackers to cause a denial of service video-capture outage via a packet to UDP port 69...

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models Via Objective-Decoupled Optimization

Vision-Language-Action VLA models have advanced robotic control by enabling end-to-end decision-making directly from multimodal inputs. However, their tightly coupled architectures expose novel security vulnerabilities. Unlike traditional adversarial perturbations, backdoor attacks represent a...

Blind Spot Navigation: Evolutionary Discovery of Sensitive Semantic Concepts for LVLMs

Whitepaper called Blind Spot Navigation: Evolutionary Discovery Of Sensitive Semantic Concepts For LVLMs...

Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study

Rapid deployment of vision-language models VLMs magnifies safety risks, yet most evaluations rely on artificial images. This study asks: How safe are current VLMs when confronted with meme images that ordinary users share? To investigate this question, we introduce MemeSafetyBench, a...