ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls

Large Language Models LLMs have demonstrated impressive fluency and reasoning capabilities, but their potential for misuse has raised growing concern. In this paper, we present ScamAgent, an autonomous multi-turn agent built on top of LLMs, capable of generating highly realistic scam call scripts...

Large Reasoning Models Are Autonomous Jailbreak Agents

Jailbreaking -- bypassing built-in safety mechanisms in AI models -- has traditionally required complex technical procedures or specialized human expertise. In this study, we show that the persuasive capabilities of large reasoning models LRMs simplify and scale jailbreaking, converting it into a...

HPE Telco Service Activator 安全漏洞

HPE Telco Service Activator is a workflow automation platform that enables automated service turn-up from HPE America. A security vulnerability exists in HPE Telco Service Activator that stems from vulnerability to cross-site scripting attacks...

HPE Telco Service Activator 安全漏洞

HPE Telco Service Activator is a workflow automation platform that enables automated service turn-up from HPE America. A security vulnerability exists in HPE Telco Service Activator that stems from vulnerability to cross-site scripting attacks...

RedCoder: Automated Multi-Turn Red Teaming for Code LLMs

Large Language Models LLMs for code generation i.e., Code LLMs have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studies have shown that these models are prone to generating vulnerable or even malicious code under adversarial settings...

Echo Chamber Jailbreak Tricks LLMs Like OpenAI and Google into Generating Harmful Content

Cybersecurity researchers are calling attention to a new jailbreaking method called Echo Chamber that could be leveraged to trick popular large language models LLMs into generating undesirable responses, irrespective of the safeguards put in place. "Unlike traditional jailbreaks that rely on...

Shuffling Cards When You Are of Very Little Brain: Low Memory Generation of Permutations

How can we generate a permutation of the numbers $1$ through $n$ so that it is hard to guess the next element given the history so far? The twist is that the generator of the permutation the "Dealer" has limited memory, while the "Guesser" has unlimited memory. With unbounded memory actually $n$...

Lifelong Safety Alignment for Language Models

LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more critical to prepare LLMs for unseen attacks that may arise duri...

CVE-2023-21461

Improper authorization vulnerability in AutoPowerOnOffConfirmDialog in Settings prior to SMR Mar-2023 Release 1 allows local attacker to turn device off via unprotected activity...

CVE-2023-1341

The RapidLoad Power-Up for Autoptimize plugin for WordPress is vulnerable to Cross-Site Request Forgery in versions up to, and including, 1.7.1. This is due to missing or incorrect nonce validation on the ajaxdeactivate function. This makes it possible for unauthenticated attackers to turn off...

CVE-2020-11805

Pexip Reverse Proxy and TURN Server before 6.1.0 has Incorrect UDP Access Control via TURN...

CVE-2020-27611

BigBlueButton through 2.2.28 uses STUN/TURN resources from a third party, which may represent an unintended endpoint...

MTSA: Multi-Turn Safety Alignment for LLMs through Multi-Round Red-Teaming

Whitepaper called MTSA: Multi-Turn Safety Alignment For LLMs Through Multi-Round Red-Teaming...

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...

X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

Multi-turn interactions with language models LMs pose critical safety risks, as harmful intent can be strategically spread across exchanges. Yet, the vast majority of prior work has focused on single-turn safety, while adaptability and diversity remain among the key challenges of multi-turn...

CVE-2024-46669

An Integer Overflow or Wraparound vulnerability CWE-190 in version 7.4.4 and below, version 7.2.10 and below; FortiSASE version 23.4.b FortiOS tenant IPsec IKE service may allow an authenticated attacker to crash the IPsec tunnel via crafted requests, resulting in potential denial of service...

New AI Jailbreak Method 'Bad Likert Judge' Boosts Attack Success Rates by Over 60%

Cybersecurity researchers have shed light on a new jailbreak technique that could be used to get past a large language model's LLM safety guardrails and produce potentially harmful or malicious responses. The multi-turn aka many-shot attack strategy has been codenamed Bad Likert Judge by Palo Alt...

PJSIP: Heap Buffer Overflow

Background PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. Description Please review the CVE identifier referenced below for details. Impact Please review the CVE identifier...

Fedora: Security Advisory for libre (FEDORA-2024-a63e807450)

The remote host is missing an update for the SPDX-FileCopyrightText: 2024 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only ifdescription...

Fedora: Security Advisory for baresip (FEDORA-2024-a15fe3f120)

The remote host is missing an update for the SPDX-FileCopyrightText: 2024 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only ifdescription...