Cisco Finds Open-Weight AI Models Easy to Exploit in Long Chats_HACKREAD:A3A5057F2D220C1FDBB033B833F35310

{
    "lastseen": "2025-11-11T12:05:08",
    "description": "Cisco\u2019s new research shows that open-weight AI models, while driving innovation, face serious security risks as multi-turn attacks, including conversational persistence, can bypass safeguards and expose data.",
    "published": "2025-11-11T10:35:42",
    "modified": "2025-11-11T10:35:42",
    "type": "hackread",
    "title": "Cisco Finds Open-Weight AI Models Easy to Exploit in Long Chats",
    "source": "",
    "references": "",
    "id": "HACKREAD:A3A5057F2D220C1FDBB033B833F35310",
    "bulletinFamily": "blog",
    "cwe": null,
    "cvelist": [],
    "sourceData": "",
    "sourceHref": "",
    "cvss": {
        "score": 0,
        "severity": "NONE",
        "vector": "NONE",
        "version": "NONE"
    },
    "cvss2": [],
    "cvss3": {
        "version": "",
        "vectorString": "",
        "baseScore": 0,
        "baseSeverity": "",
        "attackVector": "",
        "attackComplexity": "",
        "privilegesRequired": "",
        "userInteraction": "",
        "scope": "",
        "confidentialityImpact": "",
        "integrityImpact": "",
        "availabilityImpact": "",
        "cvssV3": {
            "version": "",
            "vectorString": "",
            "baseScore": 0,
            "baseSeverity": "",
            "attackVector": "",
            "attackComplexity": "",
            "privilegesRequired": "",
            "userInteraction": "",
            "scope": "",
            "confidentialityImpact": "",
            "integrityImpact": "",
            "availabilityImpact": ""
        }
    },
    "href": "https://hackread.com/cisco-open-weight-ai-models-long-chat-exploit/",
    "category_name": "News",
    "post_link": "",
    "product": "",
    "version": "",
    "vendor": "",
    "ai_description": "",
    "ai_severity": "",
    "ai_vendor": "",
    "ai_product": "",
    "ai_version": "",
    "ai_score": 0
}